AirShelf Catalog MCP · AirShelf

Operational

Unclaimed — claim this pageother Streamable HTTP2025-06-18 Auth expectations unknown

https://mcp.airshelf.ai/mcp

Badge

100%

Availability · 30 days · 349 checks

490 ms

Latency (last observation)

rev 13

Contract

27days

Schema stable

Incidents · 30 days

Aug 6, 2026

Observed since

Availability — last 30 days

No failures Some failures Mostly failing Auth required No observations

Last observed 2 h ago by MCP Tools Edge Scanner · scheduled every 120 min

Descriptions or metadata changed Informational Nov 1, 2026 — 6:10 AM

5 description/metadata changes; the functional contract is unchanged (hash sha256:ffe8f17ad52cf4eb…).

VerifiedDescriptions or metadata for compare_products changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.compare_products	description changed	Informational	Descriptions or metadata for `compare_products` changed. No structural change. Wording changes can still influence model tool selection.
tools.find_products	description changed	Informational	Descriptions or metadata for `find_products` changed. No structural change. Wording changes can still influence model tool selection.
tools.get_product	description changed	Informational	Descriptions or metadata for `get_product` changed. No structural change. Wording changes can still influence model tool selection.
tools.list_merchants	description changed	Informational	Descriptions or metadata for `list_merchants` changed. No structural change. Wording changes can still influence model tool selection.
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Oct 23, 2026 — 10:30 AM

1 description/metadata change; the functional contract is unchanged (hash sha256:ffe8f17ad52cf4eb…).

VerifiedDescriptions or metadata for search_catalog changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Potentially breaking contract changes (5) Potentially breaking Oct 5, 2026 — 12:16 PM

1 potentially breaking, 3 non-breaking changes. Default at request_quote.inputSchema.products changed from unset to [].

VerifiedDefault at request_quote.inputSchema.products changed from unset to [].

InterpretationCalls that rely on the server-side default may behave differently.

Raw event details

{
  "beforeRev": 12,
  "afterRev": 13,
  "changeCount": 5
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract changes (2) Non-breaking Sep 23, 2026 — 3:55 PM

1 non-breaking change. Optional parameter merchant was added at search_catalog.inputSchema.

VerifiedOptional parameter merchant was added at search_catalog.inputSchema.

InterpretationExisting calls are unaffected.

Raw event details

{
  "beforeRev": 11,
  "afterRev": 12,
  "changeCount": 2
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract changes (26) Non-breaking Sep 23, 2026 — 11:50 AM

25 non-breaking changes. Output field cited_field_count was added at get_product.outputSchema.product.

VerifiedOutput field cited_field_count was added at get_product.outputSchema.product.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 10,
  "afterRev": 11,
  "changeCount": 26
}

View full diff Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Sep 21, 2026 — 12:25 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:69044b14f1e3d925…).

VerifiedDescriptions or metadata for get_product changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.get_product	description changed	Informational	Descriptions or metadata for `get_product` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Sep 7, 2026 — 10:00 AM

2 description/metadata changes; the functional contract is unchanged (hash sha256:69044b14f1e3d925…).

VerifiedDescriptions or metadata for explain_product changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.explain_product	description changed	Informational	Descriptions or metadata for `explain_product` changed. No structural change. Wording changes can still influence model tool selection.
tools.get_product	description changed	Informational	Descriptions or metadata for `get_product` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 22, 2026 — 6:51 AM

1 description/metadata change; the functional contract is unchanged (hash sha256:69044b14f1e3d925…).

VerifiedDescriptions or metadata for search_catalog changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Non-breaking contract changes (2) Non-breaking Aug 17, 2026 — 8:15 AM

1 non-breaking change. Output field related_products was added at get_product.outputSchema.

VerifiedOutput field related_products was added at get_product.outputSchema.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 9,
  "afterRev": 10,
  "changeCount": 2
}

View full diff Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 15, 2026 — 6:50 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:f54ea1235977e28d…).

VerifiedDescriptions or metadata for search_catalog changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 12, 2026 — 5:55 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:f54ea1235977e28d…).

VerifiedDescriptions or metadata for search_catalog changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Non-breaking contract changes (3) Non-breaking Aug 12, 2026 — 9:35 AM

2 non-breaking changes. Output field live_discovery was added at find_products.outputSchema.

VerifiedOutput field live_discovery was added at find_products.outputSchema.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 8,
  "afterRev": 9,
  "changeCount": 3
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract change: research_shopping.outputSchema.accepted_defaults Non-breaking Aug 10, 2026 — 11:45 AM

1 non-breaking change. Output field accepted_defaults was added at research_shopping.outputSchema.

VerifiedOutput field accepted_defaults was added at research_shopping.outputSchema.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 7,
  "afterRev": 8,
  "changeCount": 1
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract changes (2) Non-breaking Aug 10, 2026 — 5:30 AM

2 non-breaking changes. Output field reason was added at search_catalog.outputSchema.

VerifiedOutput field reason was added at search_catalog.outputSchema.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 6,
  "afterRev": 7,
  "changeCount": 2
}

View full diff Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 10, 2026 — 1:20 AM

1 description/metadata change; the functional contract is unchanged (hash sha256:174fd0d5963b0b57…).

VerifiedDescriptions or metadata for research_shopping changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.research_shopping	description changed	Informational	Descriptions or metadata for `research_shopping` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Breaking contract change: search_catalog.inputSchema.q Breaking Aug 9, 2026 — 12:50 PM

1 breaking change. minLength at search_catalog.inputSchema.q was set to 0.

VerifiedminLength at search_catalog.inputSchema.q was set to 0.

InterpretationExisting calls outside the new bound may fail schema validation.

Raw event details

{
  "beforeRev": 5,
  "afterRev": 6,
  "changeCount": 1
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract change: find_products.outputSchema.status Non-breaking Aug 9, 2026 — 8:40 AM

1 non-breaking change. find_products.outputSchema.status now also accepts refused.

Verifiedfind_products.outputSchema.status now also accepts refused.

InterpretationExisting calls are unaffected.

Raw event details

{
  "beforeRev": 4,
  "afterRev": 5,
  "changeCount": 1
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract change: find_products.outputSchema.reason Non-breaking Aug 9, 2026 — 4:31 AM

1 non-breaking change. Output field reason was added at find_products.outputSchema.

VerifiedOutput field reason was added at find_products.outputSchema.

InterpretationAdditional fields are typically ignored by existing consumers.

Raw event details

{
  "beforeRev": 3,
  "afterRev": 4,
  "changeCount": 1
}

View full diff Observed by MCP Tools Edge Scanner

Descriptions or metadata changed Informational Aug 8, 2026 — 8:10 PM

1 description/metadata change; the functional contract is unchanged (hash sha256:f2540886179ba9b6…).

VerifiedDescriptions or metadata for search_catalog changed.

InterpretationNo structural change. Wording changes can still influence model tool selection.

Path	Change	Classification	Detail
tools.search_catalog	description changed	Informational	Descriptions or metadata for `search_catalog` changed. No structural change. Wording changes can still influence model tool selection.

Observed by MCP Tools Edge Scanner

Non-breaking contract changes (4) Non-breaking Aug 7, 2026 — 12:56 PM

2 non-breaking changes. find_products.outputSchema.status now also accepts no_match.

Verifiedfind_products.outputSchema.status now also accepts no_match.

InterpretationExisting calls are unaffected.

Raw event details

{
  "beforeRev": 2,
  "afterRev": 3,
  "changeCount": 4
}

View full diff Observed by MCP Tools Edge Scanner

Non-breaking contract changes (2) Non-breaking Aug 6, 2026 — 12:05 PM

1 non-breaking change. Optional parameter persona was added at research_shopping.inputSchema.

VerifiedOptional parameter persona was added at research_shopping.inputSchema.

InterpretationExisting calls are unaffected.

Raw event details

{
  "beforeRev": 1,
  "afterRev": 2,
  "changeCount": 2
}

View full diff Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 5:25 AM

8 tools, 3 resources, 0 prompts observed. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

VerifiedCanonical contract hash sha256:7d9c118b3a68ec80… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:7d9c118b3a68ec80d744e8cd300bbe1bbe4a751312ecee6235c9ac3c3f9b8646"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 8 Resources · 3 Prompts Logging Completions Experimental

Tools 8

search_catalog 6 params · 1 required Search the AirShelf cross-vendor product catalog by natural-language query. The catalog covers industrial-auto…

Search the AirShelf cross-vendor product catalog by natural-language query. The catalog covers industrial-automation, wiring-devices, digital-signage, business-display, mfp, barcode-printer, laser-printer, inkjet-printer, mechanical-keyboards, cybersecurity, threat-intelligence-platform. Industrial-automation and wiring-device rows are indexed by manufacturer part number, so a brand or part number in the query ("Pepperl+Fuchs retroreflective sensor", "IN5409") retrieves more reliably than a bare product type; those rows carry no normalized spec facets, so the `specs` filter does not apply to them. Returns ranked products with prices, specs, and per-row match accounting. Each row includes `unverified_specs`, the normalized spec names that lack claim-level receipts; never use those as decisive facts. Example queries: "tactile mechanical keyboard under $150", "Toshiba A3 colour multifunction device", "industrial barcode printer for a warehouse", "threat-intelligence platform with dark-web monitoring". Result fields: • canonical_name — the exact catalog name of the product. • spec_absence_note — spec fields absent from this product's golden record (AirShelf's verified product record); null when nothing is missing. • constraint_match_score and matched_criteria — query constraints supported by claim-level receipts. unverified_criteria names matching catalog values that still need confirmation; missing_criteria names values that are absent or conflict. • parsed.price_availability — all_null = true means every returned price is null. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error; query_had_budget reports whether the query carried one. • result.commercial_data — branch on actionable before using price or stock. Observations older than 24 hours are withheld from result.price/result.inStock and retained only as labelled last_observed history. • parsed.weak_match — the response contains an unresolved constraint, query match, or product-identity warning. parsed.unverified_identity_count counts returned names without an identity receipt. parsed.no_match — no product satisfies a hard constraint, and candidates violating it were excluded server-side. On a miss or near-miss for a specific brand+model the response may also carry a `tier3` block, meaning a real-time lookup for the exact SKU asked about; it can appear alongside fuzzy-neighbour rows. • tier3.status = "resolved" — a single-source reading of the page at tier3.source_url. MPN-confirmed means the live lookup matched the manufacturer part number. Its verification is "live-unverified": confirmed on a live page during this run, but not yet matched to an AirShelf catalog record. A verified row is matched to the catalog record. tier3.cached = true means it came from a recent prior lookup, with fetched_at recording when the page was read. • tier3.status = "abstain" — the lookup could not confirm the product exists as asked, so no specs, price, or availability were established. tier3.guidance describes the quote-request path. • tier3.status = "declined" — an applicable lookup did not run; tier3.reason says why (disabled, rate_limited, daily_cap, negative_cache, error). No specs or availability were established, and none should be inferred. No tier3 block at all means a live lookup was not applicable to this query (no parseable brand+model identity). Optional `market` (ISO 3166-1 alpha-2, e.g. "TH") excludes catalog rows whose country-specific URL conflicts with the buyer market and scopes tier3 lookup/cache. A remaining global URL is not local-availability proof: parsed.weak_match stays true and unsatisfied_constraints includes market_availability until every returned row has a matching country receipt. "Available in <market>" still does not guarantee stock.

Input schema

Parameter	Type	Description & constraints
q*	string	Natural-language query, at most 200 characters. Supports budget hints (e.g. "under $150"). minLen: 0 · maxLen: 200
category	string	Optional category filter (industrial-automation, wiring-devices, digital-signage, business-display, mfp, barcode-printer, laser-printer, inkjet-printer, mechanical-keyboards, cybersecurity, threat-intelligence-platform)
limit	integer	Max results min: 1 · max: 200 · default: 20
market	string	Buyer market as an assigned ISO 3166-1 alpha-2 country code (e.g. "TH", "AU"). Conflicting country receipts are excluded; global URLs remain market-unverified.
merchant	string	Optional merchant slug (e.g. "toshiba", "cyble") from list_merchants. Scopes the search to that merchant's own shelf, which is a SEPARATE substrate from the cross-vendor catalog: it is reached only when the cross-vendor catalog returns nothing, and its rows carry the merchant's own product data rather than datasheet-extracted golden records. Omit it for cross-vendor search, which is the default and the right choice for "what should I buy". pattern: ^[a-z0-9][a-z0-9-]{0,62}$
specs	object	Hard spec facets, e.g. {"form_factor":"desktop","print_speed_ppm":33}. Filters by exact/range spec match.

Output schema

Parameter	Type	Description & constraints
status	enum(1)	— one of: "refused"
reason	string	—
results*	array<object>	—
results[].slug*	string	—
results[].canonical_name	string	—
results[].manufacturer	string	—
results[].modelName	string	—
results[].price	number \| null	—
results[].currency	string \| null	—
results[].category	string	—
results[].qualityScore	number	—
results[].constraint_match_score	number	—
results[].spec_absence_note	string \| null	—
count	number	—
query	string	—
parsed	object	—
took_ms	number	—
tier3	object	—
tier3.tier*	number	—
tier3.status*	enum(3)	— one of: "resolved", "abstain", "declined"
tier3.reason	string	—
tier3.guidance	string	—
tier3.identity	object	—
tier3.identity.brand*	string	—
tier3.identity.model*	string	—
tier3.mpn_confirmed	boolean	—
tier3.source_url	string	—
tier3.source_tier	string	—
tier3.cached	boolean	—
tier3.verification	string	—
tier3.product	object	—

Raw schema JSON

search_catalog — raw

{
  "name": "search_catalog",
  "description": "Search the AirShelf cross-vendor product catalog by natural-language query. The catalog covers industrial-automation, wiring-devices, digital-signage, business-display, mfp, barcode-printer, laser-printer, inkjet-printer, mechanical-keyboards, cybersecurity, threat-intelligence-platform. Industrial-automation and wiring-device rows are indexed by manufacturer part number, so a brand or part number in the query (\"Pepperl+Fuchs retroreflective sensor\", \"IN5409\") retrieves more reliably than a bare product type; those rows carry no normalized spec facets, so the `specs` filter does not apply to them. Returns ranked products with prices, specs, and per-row match accounting.\nEach row includes `unverified_specs`, the normalized spec names that lack claim-level receipts; never use those as decisive facts.\nExample queries: \"tactile mechanical keyboard under $150\", \"Toshiba A3 colour multifunction device\", \"industrial barcode printer for a warehouse\", \"threat-intelligence platform with dark-web monitoring\".\n\nResult fields:\n• canonical_name — the exact catalog name of the product.\n• spec_absence_note — spec fields absent from this product&#39;s golden record (AirShelf&#39;s verified product record); null when nothing is missing.\n• constraint_match_score and matched_criteria — query constraints supported by claim-level receipts. unverified_criteria names matching catalog values that still need confirmation; missing_criteria names values that are absent or conflict.\n• parsed.price_availability — all_null = true means every returned price is null. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error; query_had_budget reports whether the query carried one.\n• result.commercial_data — branch on actionable before using price or stock. Observations older than 24 hours are withheld from result.price/result.inStock and retained only as labelled last_observed history.\n• parsed.weak_match — the response contains an unresolved constraint, query match, or product-identity warning. parsed.unverified_identity_count counts returned names without an identity receipt. parsed.no_match — no product satisfies a hard constraint, and candidates violating it were excluded server-side.\n\nOn a miss or near-miss for a specific brand+model the response may also carry a `tier3` block, meaning a real-time lookup for the exact SKU asked about; it can appear alongside fuzzy-neighbour rows.\n• tier3.status = \"resolved\" — a single-source reading of the page at tier3.source_url. MPN-confirmed means the live lookup matched the manufacturer part number. Its verification is \"live-unverified\": confirmed on a live page during this run, but not yet matched to an AirShelf catalog record. A verified row is matched to the catalog record. tier3.cached = true means it came from a recent prior lookup, with fetched_at recording when the page was read.\n• tier3.status = \"abstain\" — the lookup could not confirm the product exists as asked, so no specs, price, or availability were established. tier3.guidance describes the quote-request path.\n• tier3.status = \"declined\" — an applicable lookup did not run; tier3.reason says why (disabled, rate_limited, daily_cap, negative_cache, error). No specs or availability were established, and none should be inferred.\nNo tier3 block at all means a live lookup was not applicable to this query (no parseable brand+model identity).\n\nOptional `market` (ISO 3166-1 alpha-2, e.g. \"TH\") excludes catalog rows whose country-specific URL conflicts with the buyer market and scopes tier3 lookup/cache. A remaining global URL is not local-availability proof: parsed.weak_match stays true and unsatisfied_constraints includes market_availability until every returned row has a matching country receipt. \"Available in <market>\" still does not guarantee stock.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "q": {
        "type": "string",
        "description": "Natural-language query, at most 200 characters. Supports budget hints (e.g. \"under $150\").",
        "minLength": 0,
        "maxLength": 200
      },
      "category": {
        "description": "Optional category filter (industrial-automation, wiring-devices, digital-signage, business-display, mfp, barcode-printer, laser-printer, inkjet-printer, mechanical-keyboards, cybersecurity, threat-intelligence-platform)",
        "type": "string"
      },
      "limit": {
        "default": 20,
        "description": "Max results",
        "type": "integer",
        "minimum": 1,
        "maximum": 200
      },
      "market": {
        "description": "Buyer market as an assigned ISO 3166-1 alpha-2 country code (e.g. \"TH\", \"AU\"). Conflicting country receipts are excluded; global URLs remain market-unverified.",
        "type": "string"
      },
      "merchant": {
        "description": "Optional merchant slug (e.g. \"toshiba\", \"cyble\") from list_merchants. Scopes the search to that merchant&#39;s own shelf, which is a SEPARATE substrate from the cross-vendor catalog: it is reached only when the cross-vendor catalog returns nothing, and its rows carry the merchant&#39;s own product data rather than datasheet-extracted golden records. Omit it for cross-vendor search, which is the default and the right choice for \"what should I buy\".",
        "type": "string",
        "pattern": "^[a-z0-9][a-z0-9-]{0,62}$"
      },
      "specs": {
        "description": "Hard spec facets, e.g. {\"form_factor\":\"desktop\",\"print_speed_ppm\":33}. Filters by exact/range spec match.",
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "anyOf": [
            {
              "type": "number"
            },
            {
              "type": "string"
            },
            {
              "type": "boolean"
            }
          ]
        }
      }
    },
    "required": [
      "q"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "status": {
        "type": "string",
        "enum": [
          "refused"
        ]
      },
      "reason": {
        "type": "string"
      },
      "results": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "slug": {
              "type": "string"
            },
            "canonical_name": {
              "type": "string"
            },
            "manufacturer": {
              "type": "string"
            },
            "modelName": {
              "type": "string"
            },
            "price": {
              "anyOf": [
                {
                  "type": "number"
                },
                {
                  "type": "null"
                }
              ]
            },
            "currency": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "null"
                }
              ]
            },
            "category": {
              "type": "string"
            },
            "qualityScore": {
              "type": "number"
            },
            "constraint_match_score": {
              "type": "number"
            },
            "spec_absence_note": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "null"
                }
              ]
            }
          },
          "required": [
            "slug"
          ],
          "additionalProperties": {}
        }
      },
      "count": {
        "type": "number"
      },
      "query": {
        "type": "string"
      },
      "parsed": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      },
      "took_ms": {
        "type": "number"
      },
      "tier3": {
        "type": "object",
        "properties": {
          "tier": {
            "type": "number"
          },
          "status": {
            "type": "string",
            "enum": [
              "resolved",
              "abstain",
              "declined"
            ]
          },
          "reason": {
            "type": "string"
          },
          "guidance": {
            "type": "string"
          },
          "identity": {
            "type": "object",
            "properties": {
              "brand": {
                "type": "string"
              },
              "model": {
                "type": "string"
              }
            },
            "required": [
              "brand",
              "model"
            ],
            "additionalProperties": false
          },
          "mpn_confirmed": {
            "type": "boolean"
          },
          "source_url": {
            "type": "string"
          },
          "source_tier": {
            "type": "string"
          },
          "cached": {
            "type": "boolean"
          },
          "verification": {
            "type": "string"
          },
          "product": {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {}
          }
        },
        "required": [
          "tier",
          "status"
        ],
        "additionalProperties": {}
      }
    },
    "required": [
      "results"
    ],
    "additionalProperties": false
  }
}

find_products 3 params · 1 required Discover candidate products for a buyer need. Takes a need in natural language (e.g. "best value home espresso…

Discover candidate products for a buyer need. Takes a need in natural language (e.g. "best value home espresso machine", market "TH"), checks the verified catalog first, then uses live web discovery only when the catalog has no candidates. Returns up to 3 candidates with explicit fit accounting. find_products is the quick candidate-list tool; research_shopping is the full verified-research job. For a specific brand+model, search_catalog is cheaper and returns the same live-lookup block on a miss. Response fields: • candidates[].verification — "catalog-candidate" for a catalog starting point whose fit still needs checking, or "live-unverified" for a live page read during this run. • candidates[].status — "resolved" means both identity and the parsed buyer constraints were supported by the cited page; "abstain" means identity or need fit could not be established. Inspect constraint_check for matched, conflicting, and unverified requirements. • candidates[].constraint_check.receipts maps each receipt-backed matched requirement to its supporting source URL and trust label. • Candidates come from current web-search results, so they are a sample of what the market offers rather than a ranking. • status at the top level — "no_match" means discovery ran but no candidate was confirmed as satisfying the need; "disabled", "rate_limited", or "unavailable" means no discovery ran. • live_discovery.status="unavailable" means receipted catalog candidates were returned while live discovery was unavailable. Optional `market` (ISO 3166-1 alpha-2) biases discovery and marketplace checks toward seller pages serving that country and scopes the lookup cache. "Available in <market>" means the seller page serves that market, not that stock is guaranteed.

Input schema

Parameter	Type	Description & constraints
need*	string	The buyer need in natural language, e.g. "quiet mechanical keyboard for open office" or "best value home espresso machine". minLen: 3 · maxLen: 200
market	string	Buyer market as ISO 3166-1 alpha-2 country code (e.g. "TH"). Biases discovery and marketplace checks toward seller pages serving that country and scopes the cache; availability is not a stock guarantee.
max	integer	Max candidates to verify (each costs a live lookup; capped at 3). min: 1 · max: 3 · default: 3

Output schema

Parameter	Type	Description & constraints
need	string	—
market	string \| null	—
status	enum(7)	— one of: "ok", "no_match", "disabled", "rate_limited", "unavailable", "error", "refused"
error	string	—
reason	string	—
verification	string	—
guidance	string	—
live_discovery	object	—
live_discovery.status*	string	—
live_discovery.reason	string	—
live_discovery.guidance	string	—
serp_considered	number	—
candidates*	array<object>	—
candidates[].query*	string	—
candidates[].tier*	number	—
candidates[].status*	enum(3)	— one of: "resolved", "abstain", "declined"
candidates[].reason	string	—
candidates[].guidance	string	—
candidates[].identity	object	—
candidates[].identity.brand*	string	—
candidates[].identity.model*	string	—
candidates[].mpn_confirmed	boolean	—
candidates[].source_url	string	—
candidates[].source_tier	string	—
candidates[].cached	boolean	—
candidates[].verification	string	—
candidates[].product	object	—
took_ms	number	—

Raw schema JSON

find_products — raw

{
  "name": "find_products",
  "description": "Discover candidate products for a buyer need. Takes a need in natural language (e.g. \"best value home espresso machine\", market \"TH\"), checks the verified catalog first, then uses live web discovery only when the catalog has no candidates. Returns up to 3 candidates with explicit fit accounting.\n\nfind_products is the quick candidate-list tool; research_shopping is the full verified-research job. For a specific brand+model, search_catalog is cheaper and returns the same live-lookup block on a miss.\n\nResponse fields:\n• candidates[].verification — \"catalog-candidate\" for a catalog starting point whose fit still needs checking, or \"live-unverified\" for a live page read during this run.\n• candidates[].status — \"resolved\" means both identity and the parsed buyer constraints were supported by the cited page; \"abstain\" means identity or need fit could not be established. Inspect constraint_check for matched, conflicting, and unverified requirements.\n• candidates[].constraint_check.receipts maps each receipt-backed matched requirement to its supporting source URL and trust label.\n• Candidates come from current web-search results, so they are a sample of what the market offers rather than a ranking.\n• status at the top level — \"no_match\" means discovery ran but no candidate was confirmed as satisfying the need; \"disabled\", \"rate_limited\", or \"unavailable\" means no discovery ran.\n\n• live_discovery.status=\"unavailable\" means receipted catalog candidates were returned while live discovery was unavailable.\n\nOptional `market` (ISO 3166-1 alpha-2) biases discovery and marketplace checks toward seller pages serving that country and scopes the lookup cache. \"Available in <market>\" means the seller page serves that market, not that stock is guaranteed.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "need": {
        "type": "string",
        "description": "The buyer need in natural language, e.g. \"quiet mechanical keyboard for open office\" or \"best value home espresso machine\".",
        "minLength": 3,
        "maxLength": 200
      },
      "market": {
        "description": "Buyer market as ISO 3166-1 alpha-2 country code (e.g. \"TH\"). Biases discovery and marketplace checks toward seller pages serving that country and scopes the cache; availability is not a stock guarantee.",
        "type": "string"
      },
      "max": {
        "default": 3,
        "description": "Max candidates to verify (each costs a live lookup; capped at 3).",
        "type": "integer",
        "minimum": 1,
        "maximum": 3
      }
    },
    "required": [
      "need"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "need": {
        "type": "string"
      },
      "market": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ]
      },
      "status": {
        "type": "string",
        "enum": [
          "ok",
          "no_match",
          "disabled",
          "rate_limited",
          "unavailable",
          "error",
          "refused"
        ]
      },
      "error": {
        "type": "string"
      },
      "reason": {
        "type": "string"
      },
      "verification": {
        "type": "string"
      },
      "guidance": {
        "type": "string"
      },
      "live_discovery": {
        "type": "object",
        "properties": {
          "status": {
            "type": "string",
            "const": "unavailable"
          },
          "reason": {
            "type": "string"
          },
          "guidance": {
            "type": "string"
          }
        },
        "required": [
          "status"
        ],
        "additionalProperties": false
      },
      "serp_considered": {
        "type": "number"
      },
      "candidates": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "query": {
              "type": "string"
            },
            "tier": {
              "type": "number"
            },
            "status": {
              "type": "string",
              "enum": [
                "resolved",
                "abstain",
                "declined"
              ]
            },
            "reason": {
              "type": "string"
            },
            "guidance": {
              "type": "string"
            },
            "identity": {
              "type": "object",
              "properties": {
                "brand": {
                  "type": "string"
                },
                "model": {
                  "type": "string"
                }
              },
              "required": [
                "brand",
                "model"
              ],
              "additionalProperties": false
            },
            "mpn_confirmed": {
              "type": "boolean"
            },
            "source_url": {
              "type": "string"
            },
            "source_tier": {
              "type": "string"
            },
            "cached": {
              "type": "boolean"
            },
            "verification": {
              "type": "string"
            },
            "product": {
              "type": "object",
              "propertyNames": {
                "type": "string"
              },
              "additionalProperties": {}
            }
          },
          "required": [
            "query",
            "tier",
            "status"
          ],
          "additionalProperties": {}
        }
      },
      "took_ms": {
        "type": "number"
      }
    },
    "required": [
      "candidates"
    ],
    "additionalProperties": false
  }
}

research_shopping 5 params research_shopping is the full verified-research job; find_products is the quick candidate-list tool. It runs a…

research_shopping is the full verified-research job; find_products is the quick candidate-list tool. It runs as a background job and returns status "running" with a research ID while the minutes-long research continues; the same research ID returns the run on later polls until completion. Unsafe medical, legal, financial-advice, and professional-service asks return status "refused" before any work is queued. Completed runs return a researched recommendation with per-claim source receipts, or an explicit refusal when evidence is insufficient. Missing decision details return clarification questions before research starts. `market` biases discovery and marketplace checks toward seller pages serving that country; "available in <market>" means the seller page serves that market, not that stock is guaranteed. Example answer keys include {"budget":"500 USD","market":"US","category":"espresso machine"}.

Input schema

Parameter	Type	Description & constraints
need	string	Buyer need in natural language. Required when starting a new research run. minLen: 1 · maxLen: 2000
market	string	Buyer market as an ISO 3166-1 alpha-2 country code. Biases discovery and marketplace checks toward seller pages serving that country; availability is not a stock guarantee.
persona	enum(2)	Research persona; b2b produces a quotation/RFQ pack. one of: "consumer", "b2b"
answers	object	Answers to clarification questions. Set accept_defaults:true to accept budget and market defaults; it does not waive product type, use case, or must-have requirements.
research_id	string	Existing research run identifier to read instead of starting a new run.

Output schema

Parameter	Type	Description & constraints
status*	enum(5)	— one of: "needs_input", "running", "complete", "failed", "refused"
research_id	string	—
accepted_defaults	object	—
questions	array<object>	—
questions[].key*	enum(3)	— one of: "budget", "market", "category"
questions[].question*	string	—
stage_counters	object	Progress counters for a running research job. Individual counters may be absent.
stage_counters.candidates_found	number	Candidates found during discovery.
stage_counters.verified	number	Candidates examined during verification, not a count of candidates that passed.
stage_counters.listings_checked	number	Market listing URLs recorded during commercial checks.
stage_counters.stage	string	Current pipeline stage identifier, or queued before work starts.
elapsed_seconds	number	—
eta_seconds	number \| null	—
outcome	enum(5) \| null	—
dossier	object	—
reason	string	—
stage	string \| null	—

Raw schema JSON

research_shopping — raw

{
  "name": "research_shopping",
  "description": "research_shopping is the full verified-research job; find_products is the quick candidate-list tool. It runs as a background job and returns status \"running\" with a research ID while the minutes-long research continues; the same research ID returns the run on later polls until completion. Unsafe medical, legal, financial-advice, and professional-service asks return status \"refused\" before any work is queued. Completed runs return a researched recommendation with per-claim source receipts, or an explicit refusal when evidence is insufficient. Missing decision details return clarification questions before research starts. `market` biases discovery and marketplace checks toward seller pages serving that country; \"available in <market>\" means the seller page serves that market, not that stock is guaranteed. Example answer keys include {\"budget\":\"500 USD\",\"market\":\"US\",\"category\":\"espresso machine\"}.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "need": {
        "description": "Buyer need in natural language. Required when starting a new research run.",
        "type": "string",
        "minLength": 1,
        "maxLength": 2000
      },
      "market": {
        "description": "Buyer market as an ISO 3166-1 alpha-2 country code. Biases discovery and marketplace checks toward seller pages serving that country; availability is not a stock guarantee.",
        "type": "string"
      },
      "persona": {
        "description": "Research persona; b2b produces a quotation/RFQ pack.",
        "type": "string",
        "enum": [
          "consumer",
          "b2b"
        ]
      },
      "answers": {
        "description": "Answers to clarification questions. Set accept_defaults:true to accept budget and market defaults; it does not waive product type, use case, or must-have requirements.",
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      },
      "research_id": {
        "description": "Existing research run identifier to read instead of starting a new run.",
        "type": "string"
      }
    }
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "status": {
        "type": "string",
        "enum": [
          "needs_input",
          "running",
          "complete",
          "failed",
          "refused"
        ]
      },
      "research_id": {
        "type": "string"
      },
      "accepted_defaults": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {
          "type": "string"
        }
      },
      "questions": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "key": {
              "type": "string",
              "enum": [
                "budget",
                "market",
                "category"
              ]
            },
            "question": {
              "type": "string"
            }
          },
          "required": [
            "key",
            "question"
          ],
          "additionalProperties": false
        }
      },
      "stage_counters": {
        "description": "Progress counters for a running research job. Individual counters may be absent.",
        "type": "object",
        "properties": {
          "candidates_found": {
            "description": "Candidates found during discovery.",
            "type": "number"
          },
          "verified": {
            "description": "Candidates examined during verification, not a count of candidates that passed.",
            "type": "number"
          },
          "listings_checked": {
            "description": "Market listing URLs recorded during commercial checks.",
            "type": "number"
          },
          "stage": {
            "description": "Current pipeline stage identifier, or queued before work starts.",
            "type": "string"
          }
        },
        "additionalProperties": {}
      },
      "elapsed_seconds": {
        "type": "number"
      },
      "eta_seconds": {
        "anyOf": [
          {
            "type": "number"
          },
          {
            "type": "null"
          }
        ]
      },
      "outcome": {
        "anyOf": [
          {
            "type": "string",
            "enum": [
              "recommend",
              "conditional",
              "insufficient_evidence",
              "no_candidate_passes",
              "defer"
            ]
          },
          {
            "type": "null"
          }
        ]
      },
      "dossier": {},
      "reason": {
        "type": "string"
      },
      "stage": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ]
      }
    },
    "required": [
      "status"
    ],
    "additionalProperties": false
  }
}

get_product 1 param · 1 required Get the full golden record (AirShelf's verified product record) and latest price for one catalog product by sl…

Get the full golden record (AirShelf's verified product record) and latest price for one catalog product by slug ("<manufacturer>-<model>"). Returns the product's specs and provenance (which page each fact came from), plus canonical_name (its exact catalog name). A field's evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. Branch on commercial_data.actionable before using price or stock: observations older than 24 hours are withheld from latestPrice and retained only as labelled last_observed history. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error. In clients that render MCP Apps the response also draws one product card per call. related_products — relationships extracted from vendor documents (e.g. compatible toner or drum accessories with their source quotes, functional equivalents, supersessions); each entry names the related catalog slug, the relation type, its direction (direction is "from_this" when the relation reads this-product → related-product, "to_this" when it reads related-product → this-product), and the source URL and quote the relation was extracted from.

Input schema

Parameter	Type	Description & constraints
slug*	string	Composite slug, e.g. toshiba-b-ex4t1-ts12-qm-r minLen: 1

Output schema

Parameter	Type	Description & constraints
imageUrl	string	—
title*	string	—
benefits	array<string>	—
productId*	string	—
buyUrl	string	—
buttonLabel*	string	—
action*	enum(2)	— one of: "quote", "link"
pricing_gated	boolean	—
related_products	array<object>	Documented related catalog products, including accessories, equivalents and replacements.
related_products[].slug*	string	—
related_products[].relation*	string	Relationship type recorded from vendor documents.
related_products[].direction*	enum(2)	from_this means this product points to the related product; to_this means the reverse. one of: "from_this", "to_this"
related_products[].source	object \| null	Stored source URL, quote, section or page for the relationship; null when none was recorded.
product	object	—
product.lifecycle_status	enum(2)	Retirement marker from stored product evidence. current means no retirement marker was found. one of: "current", "retired"
product.pdfFilenames	array<string>	Stored source PDF filenames. A filename is not a download URL.
product.sources	array<object \| string> \| object \| null	Stored evidence sources. Imports may preserve a source object, use ref instead of url, or list plain strings. Null when unavailable.
product.latestPrice	object \| null	Latest valid price observation within 24 hours. Null when absent or stale; stale history remains in commercial_data.last_observed.
product.related_products	array<object>	Documented related catalog products, including accessories, equivalents and replacements.
product.related_products[].slug*	string	—
product.related_products[].relation*	string	Relationship type recorded from vendor documents.
product.related_products[].direction*	enum(2)	from_this means this product points to the related product; to_this means the reverse. one of: "from_this", "to_this"
product.related_products[].source	object \| null	Stored source URL, quote, section or page for the relationship; null when none was recorded.
product.updatedAt	string	Catalog row update time as an ISO 8601 timestamp, not a per-claim verification time.
product.qualityScore	number	Percentage of golden-record fields with claim-level citations. Zero when there are no fields.
product.cited_field_count	number	Number of golden-record fields with claim-level citations.
product.field_count	number	Total golden-record fields used as the evidence coverage denominator.

Raw schema JSON

get_product — raw

{
  "name": "get_product",
  "description": "Get the full golden record (AirShelf&#39;s verified product record) and latest price for one catalog product by slug (\"<manufacturer>-<model>\").\n\nReturns the product&#39;s specs and provenance (which page each fact came from), plus canonical_name (its exact catalog name). A field&#39;s evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. Branch on commercial_data.actionable before using price or stock: observations older than 24 hours are withheld from latestPrice and retained only as labelled last_observed history. For quote-gated B2B pricing, a null price with a quote path is expected rather than an error. In clients that render MCP Apps the response also draws one product card per call. related_products — relationships extracted from vendor documents (e.g. compatible toner or drum accessories with their source quotes, functional equivalents, supersessions); each entry names the related catalog slug, the relation type, its direction (direction is \"from_this\" when the relation reads this-product → related-product, \"to_this\" when it reads related-product → this-product), and the source URL and quote the relation was extracted from.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "slug": {
        "type": "string",
        "minLength": 1,
        "description": "Composite slug, e.g. toshiba-b-ex4t1-ts12-qm-r"
      }
    },
    "required": [
      "slug"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "imageUrl": {
        "type": "string"
      },
      "title": {
        "type": "string"
      },
      "benefits": {
        "type": "array",
        "items": {
          "type": "string"
        }
      },
      "productId": {
        "type": "string"
      },
      "buyUrl": {
        "type": "string"
      },
      "buttonLabel": {
        "type": "string"
      },
      "action": {
        "type": "string",
        "enum": [
          "quote",
          "link"
        ]
      },
      "pricing_gated": {
        "type": "boolean"
      },
      "related_products": {
        "description": "Documented related catalog products, including accessories, equivalents and replacements.",
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "slug": {
              "type": "string"
            },
            "relation": {
              "type": "string",
              "description": "Relationship type recorded from vendor documents."
            },
            "direction": {
              "type": "string",
              "enum": [
                "from_this",
                "to_this"
              ],
              "description": "from_this means this product points to the related product; to_this means the reverse."
            },
            "source": {
              "description": "Stored source URL, quote, section or page for the relationship; null when none was recorded.",
              "anyOf": [
                {
                  "type": "object",
                  "propertyNames": {
                    "type": "string"
                  },
                  "additionalProperties": {}
                },
                {
                  "type": "null"
                }
              ]
            }
          },
          "required": [
            "slug",
            "relation",
            "direction"
          ],
          "additionalProperties": {}
        }
      },
      "product": {
        "type": "object",
        "properties": {
          "lifecycle_status": {
            "description": "Retirement marker from stored product evidence. current means no retirement marker was found.",
            "type": "string",
            "enum": [
              "current",
              "retired"
            ]
          },
          "pdfFilenames": {
            "description": "Stored source PDF filenames. A filename is not a download URL.",
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "sources": {
            "description": "Stored evidence sources. Imports may preserve a source object, use ref instead of url, or list plain strings. Null when unavailable.",
            "anyOf": [
              {
                "anyOf": [
                  {
                    "type": "array",
                    "items": {
                      "anyOf": [
                        {
                          "type": "object",
                          "properties": {
                            "url": {
                              "description": "Source document or product-page URL when recorded.",
                              "anyOf": [
                                {
                                  "type": "string"
                                },
                                {
                                  "type": "null"
                                }
                              ]
                            },
                            "type": {
                              "description": "Stored source type, such as pdf or product_page.",
                              "anyOf": [
                                {
                                  "type": "string"
                                },
                                {
                                  "type": "null"
                                }
                              ]
                            }
                          },
                          "additionalProperties": {}
                        },
                        {
                          "type": "string"
                        }
                      ]
                    }
                  },
                  {
                    "type": "object",
                    "propertyNames": {
                      "type": "string"
                    },
                    "additionalProperties": {}
                  }
                ]
              },
              {
                "type": "null"
              }
            ]
          },
          "latestPrice": {
            "description": "Latest valid price observation within 24 hours. Null when absent or stale; stale history remains in commercial_data.last_observed.",
            "anyOf": [
              {
                "type": "object",
                "properties": {
                  "price": {
                    "type": "number"
                  },
                  "currency": {
                    "anyOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "null"
                      }
                    ]
                  },
                  "retailer": {
                    "anyOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "null"
                      }
                    ]
                  },
                  "inStock": {
                    "anyOf": [
                      {
                        "type": "boolean"
                      },
                      {
                        "type": "null"
                      }
                    ]
                  },
                  "capturedAt": {
                    "type": "string"
                  }
                },
                "required": [
                  "price",
                  "currency",
                  "retailer",
                  "inStock",
                  "capturedAt"
                ],
                "additionalProperties": {}
              },
              {
                "type": "null"
              }
            ]
          },
          "related_products": {
            "description": "Documented related catalog products, including accessories, equivalents and replacements.",
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "slug": {
                  "type": "string"
                },
                "relation": {
                  "type": "string",
                  "description": "Relationship type recorded from vendor documents."
                },
                "direction": {
                  "type": "string",
                  "enum": [
                    "from_this",
                    "to_this"
                  ],
                  "description": "from_this means this product points to the related product; to_this means the reverse."
                },
                "source": {
                  "description": "Stored source URL, quote, section or page for the relationship; null when none was recorded.",
                  "anyOf": [
                    {
                      "type": "object",
                      "propertyNames": {
                        "type": "string"
                      },
                      "additionalProperties": {}
                    },
                    {
                      "type": "null"
                    }
                  ]
                }
              },
              "required": [
                "slug",
                "relation",
                "direction"
              ],
              "additionalProperties": {}
            }
          },
          "updatedAt": {
            "description": "Catalog row update time as an ISO 8601 timestamp, not a per-claim verification time.",
            "type": "string"
          },
          "qualityScore": {
            "description": "Percentage of golden-record fields with claim-level citations. Zero when there are no fields.",
            "type": "number"
          },
          "cited_field_count": {
            "description": "Number of golden-record fields with claim-level citations.",
            "type": "number"
          },
          "field_count": {
            "description": "Total golden-record fields used as the evidence coverage denominator.",
            "type": "number"
          }
        },
        "additionalProperties": {}
      }
    },
    "required": [
      "title",
      "productId",
      "buttonLabel",
      "action"
    ],
    "additionalProperties": false
  }
}

compare_products 2 params · 1 required Compare 2-10 catalog products side-by-side on their datasheet specs. Slugs come from search_catalog and are ca…

Compare 2-10 catalog products side-by-side on their datasheet specs. Slugs come from search_catalog and are case-insensitive and dash-tolerant ("e-STUDIO 331AC", "toshiba-e-studio-331ac" and "e-studio331ac" all resolve to the same product). Returns one item per product with canonical_name and spec_absence_note (spec fields absent from that product's golden record, AirShelf's verified product record). Branch on each item's commercial_data.actionable before using price or stock; stale observations are withheld from action fields. A slug that does not resolve comes back as not_found with a did_you_mean suggestion. The `provenance` option adds the source page and source type already stored with each fact.

Input schema

Parameter	Type	Description & constraints
slugs*	array<string>	Catalog slugs to compare
provenance	boolean	Include the stored source page and source type for each fact

Output schema

Parameter	Type	Description & constraints
items*	array<object>	—
items[].slug*	string	—
items[].canonical_name	string	—
items[].manufacturer	string	—
items[].modelName	string	—
items[].price	number \| null	—
items[].spec_absence_note	string \| null	—
count	number	—

Raw schema JSON

compare_products — raw

{
  "name": "compare_products",
  "description": "Compare 2-10 catalog products side-by-side on their datasheet specs. Slugs come from search_catalog and are case-insensitive and dash-tolerant (\"e-STUDIO 331AC\", \"toshiba-e-studio-331ac\" and \"e-studio331ac\" all resolve to the same product).\n\nReturns one item per product with canonical_name and spec_absence_note (spec fields absent from that product&#39;s golden record, AirShelf&#39;s verified product record). Branch on each item&#39;s commercial_data.actionable before using price or stock; stale observations are withheld from action fields. A slug that does not resolve comes back as not_found with a did_you_mean suggestion. The `provenance` option adds the source page and source type already stored with each fact.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "slugs": {
        "minItems": 2,
        "maxItems": 10,
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        },
        "description": "Catalog slugs to compare"
      },
      "provenance": {
        "description": "Include the stored source page and source type for each fact",
        "type": "boolean"
      }
    },
    "required": [
      "slugs"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "items": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "slug": {
              "type": "string"
            },
            "canonical_name": {
              "type": "string"
            },
            "manufacturer": {
              "type": "string"
            },
            "modelName": {
              "type": "string"
            },
            "price": {
              "anyOf": [
                {
                  "type": "number"
                },
                {
                  "type": "null"
                }
              ]
            },
            "spec_absence_note": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "null"
                }
              ]
            }
          },
          "required": [
            "slug"
          ],
          "additionalProperties": {}
        }
      },
      "count": {
        "type": "number"
      }
    },
    "required": [
      "items"
    ],
    "additionalProperties": false
  }
}

explain_product 1 param · 1 required Explain the evidence behind a catalog row. Returns stored processing stages when available and always returns …

Explain the evidence behind a catalog row. Returns stored processing stages when available and always returns a golden-record field summary with source coverage. A field's evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. record.scraped_at is the catalog row's scrape time, not a per-claim evidence capture time.

Input schema

Parameter	Type	Description & constraints
slug*	string	Composite slug to explain minLen: 1

Output schema

Parameter	Type	Description & constraints
slug	string	—
sku	string	—
canonical_name	string	—
category	string	—
trace_status	enum(2)	— one of: "available", "not_recorded"
count	number	—
note	string	—
trace	object	—
record	object	—

Raw schema JSON

explain_product — raw

{
  "name": "explain_product",
  "description": "Explain the evidence behind a catalog row. Returns stored processing stages when available and always returns a golden-record field summary with source coverage. A field&#39;s evidence_sha256 is the SHA-256 of the source document AirShelf archived when it extracted that claim. A caller holding the same bytes can compare the hash to check that the cited document has not changed. AirShelf does not serve those archived bytes, and the hash does not promise they remain retrievable. record.scraped_at is the catalog row&#39;s scrape time, not a per-claim evidence capture time.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "slug": {
        "type": "string",
        "minLength": 1,
        "description": "Composite slug to explain"
      }
    },
    "required": [
      "slug"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "slug": {
        "type": "string"
      },
      "sku": {
        "type": "string"
      },
      "canonical_name": {
        "type": "string"
      },
      "category": {
        "type": "string"
      },
      "trace_status": {
        "type": "string",
        "enum": [
          "available",
          "not_recorded"
        ]
      },
      "count": {
        "type": "number"
      },
      "note": {
        "type": "string"
      },
      "trace": {},
      "record": {}
    },
    "additionalProperties": false
  }
}

list_merchants 0 params List public AirShelf merchants that have an assigned slug and at least one active product. Internal/demo and e…

List public AirShelf merchants that have an assigned slug and at least one active product. Internal/demo and empty catalogs are excluded. Returns each merchant's name, slug, and product count; the slug is the `merchant` argument for request_quote.

Input schema

No parameters.

Output schema

Parameter	Type	Description & constraints
merchants*	array<object>	—
merchants[].name*	string	—
merchants[].slug*	string	—
merchants[].product_count*	number	—
merchants[].domain	string	—
merchants[].manifest_url	string	Merchant agent manifest URL with supported endpoints and capabilities.
merchants[].products_url	string	Merchant product-listing endpoint URL.
merchants[].search_url	string	Merchant-scoped product-search endpoint URL.
merchants[].checkout_capability	enum(2)	shopify indicates a connected Shopify store; redirect sends the buyer to the product page. one of: "shopify", "redirect"
total	number	—

Raw schema JSON

list_merchants — raw

{
  "name": "list_merchants",
  "description": "List public AirShelf merchants that have an assigned slug and at least one active product. Internal/demo and empty catalogs are excluded. Returns each merchant&#39;s name, slug, and product count; the slug is the `merchant` argument for request_quote.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {}
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "merchants": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "name": {
              "type": "string"
            },
            "slug": {
              "type": "string"
            },
            "product_count": {
              "type": "number",
              "exclusiveMinimum": 0
            },
            "domain": {
              "type": "string"
            },
            "manifest_url": {
              "description": "Merchant agent manifest URL with supported endpoints and capabilities.",
              "type": "string"
            },
            "products_url": {
              "description": "Merchant product-listing endpoint URL.",
              "type": "string"
            },
            "search_url": {
              "description": "Merchant-scoped product-search endpoint URL.",
              "type": "string"
            },
            "checkout_capability": {
              "description": "shopify indicates a connected Shopify store; redirect sends the buyer to the product page.",
              "type": "string",
              "enum": [
                "shopify",
                "redirect"
              ]
            }
          },
          "required": [
            "name",
            "slug",
            "product_count"
          ],
          "additionalProperties": {}
        }
      },
      "total": {
        "type": "number"
      }
    },
    "required": [
      "merchants"
    ],
    "additionalProperties": false
  }
}

request_quote 7 params · 2 required Send a quote request for catalog products to a merchant's sales team on behalf of a named buyer. This is a tw…

Send a quote request for catalog products to a merchant's sales team on behalf of a named buyer. This is a two-step, double opt-in flow. The first call emails a confirmation link to `contact.email` and returns status "confirmation_required"; no lead exists and no merchant is contacted until the buyer confirms. A later call with the same arguments reports "awaiting_confirmation" while the email is unconfirmed, or "received" with a reference_number after confirmation. Merchant slugs come from list_merchants. Network-catalog brands that are absent from that list use merchant:"airshelf-network" with brandSlug:"<manufacturer-slug>"; AirShelf routes the confirmed request to that brand.

Input schema

Parameter	Type	Description & constraints
merchant*	string	Merchant slug or id (from list_merchants), or "airshelf-network" for network-catalog brands minLen: 1
products	array<string>	Catalog slugs the buyer is interested in; may be omitted when attaching contact to a rep desk reference default: []
quantity	integer	Units the buyer wants max: 9007199254740991
contact*	object	Buyer contact details
contact.name*	string	Buyer name
contact.email*	string	Buyer work email format: email · pattern: ^(?!\.)(?!.\.\.)([A-Za-z0-9_'+\-\.])[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\-]*\.)+[A-Za-z]{2,}$
contact.company	string	Buyer company
notes	string	Any extra context from the buyer
reference	string	Rep desk trace returned by ask, so confirmed contact reaches the same request pattern: ^REQ-[A-Z0-9-]{1,4}-[A-Z0-9]{6}$
brandSlug	string	Manufacturer slug (from search results) — required with merchant:"airshelf-network" so the lead reaches the right brand minLen: 1

Output schema

Parameter	Type	Description & constraints
reference_number	string	—
status	string	—
next_step	string	—

Raw schema JSON

request_quote — raw

{
  "name": "request_quote",
  "description": "Send a quote request for catalog products to a merchant&#39;s sales team on behalf of a named buyer.\n\nThis is a two-step, double opt-in flow. The first call emails a confirmation link to `contact.email` and returns status \"confirmation_required\"; no lead exists and no merchant is contacted until the buyer confirms. A later call with the same arguments reports \"awaiting_confirmation\" while the email is unconfirmed, or \"received\" with a reference_number after confirmation.\n\nMerchant slugs come from list_merchants. Network-catalog brands that are absent from that list use merchant:\"airshelf-network\" with brandSlug:\"<manufacturer-slug>\"; AirShelf routes the confirmed request to that brand.",
  "inputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "merchant": {
        "type": "string",
        "minLength": 1,
        "description": "Merchant slug or id (from list_merchants), or \"airshelf-network\" for network-catalog brands"
      },
      "products": {
        "default": [],
        "description": "Catalog slugs the buyer is interested in; may be omitted when attaching contact to a rep desk reference",
        "maxItems": 50,
        "type": "array",
        "items": {
          "type": "string",
          "minLength": 1
        }
      },
      "quantity": {
        "description": "Units the buyer wants",
        "type": "integer",
        "exclusiveMinimum": 0,
        "maximum": 9007199254740991
      },
      "contact": {
        "type": "object",
        "properties": {
          "name": {
            "type": "string",
            "description": "Buyer name"
          },
          "email": {
            "type": "string",
            "format": "email",
            "pattern": "^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_&#39;+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$",
            "description": "Buyer work email"
          },
          "company": {
            "description": "Buyer company",
            "type": "string"
          }
        },
        "required": [
          "name",
          "email"
        ],
        "description": "Buyer contact details"
      },
      "notes": {
        "description": "Any extra context from the buyer",
        "type": "string"
      },
      "reference": {
        "description": "Rep desk trace returned by ask, so confirmed contact reaches the same request",
        "type": "string",
        "pattern": "^REQ-[A-Z0-9-]{1,4}-[A-Z0-9]{6}$"
      },
      "brandSlug": {
        "description": "Manufacturer slug (from search results) — required with merchant:\"airshelf-network\" so the lead reaches the right brand",
        "type": "string",
        "minLength": 1
      }
    },
    "required": [
      "merchant",
      "contact"
    ]
  },
  "outputSchema": {
    "$schema": "http://json-schema.org/draft-07/schema#",
    "type": "object",
    "properties": {
      "reference_number": {
        "type": "string"
      },
      "status": {
        "type": "string"
      },
      "next_step": {
        "type": "string"
      }
    },
    "additionalProperties": false
  }
}

Resources 3

URI	Name	MIME type	Description
ui://airshelf/product-card.html	product_card_ui	`text/html;profile=mcp-app`	—
ui://airshelf/nda-gate.html	nda_gate_ui	`text/html;profile=mcp-app`	—
ui://airshelf/sealed-quote.html	sealed_quote_ui	`text/html;profile=mcp-app`	—

Prompts 0

No prompts advertised.

Inventory recorded Oct 5, 2026 — 12:16 PM as rev 13. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 13

sha256:ffe8f17ad52cf4ebd043b057158bd58d499414bd40cf7871f6f3df0b0ce8ccf9

Computed centrally from the normalized capability inventory (normalizer v1). Scanners submit raw observations; the control plane normalizes and hashes, so every scanner agrees on the same value.

Revisions 13

Rev	Observed	Hash
rev 13	Oct 5, 2026 — 12:16 PM (28 d ago)
rev 12	Sep 23, 2026 — 3:55 PM (39 d ago)
rev 11	Sep 23, 2026 — 11:50 AM (40 d ago)
rev 10	Aug 17, 2026 — 8:15 AM (77 d ago)
rev 9	Aug 12, 2026 — 9:35 AM (82 d ago)
rev 8	Aug 10, 2026 — 11:45 AM (84 d ago)
rev 7	Aug 10, 2026 — 5:30 AM (84 d ago)
rev 6	Aug 9, 2026 — 12:50 PM (85 d ago)
rev 5	Aug 9, 2026 — 8:40 AM (85 d ago)
rev 4	Aug 9, 2026 — 4:31 AM (85 d ago)
rev 3	Aug 7, 2026 — 12:56 PM (87 d ago)
rev 2	Aug 6, 2026 — 12:05 PM (88 d ago)
rev 1 baseline	Aug 6, 2026 — 5:25 AM (88 d ago)

Contract changes 12

Potentially breaking 1 potentially breaking, 3 non-breaking changes. Default at request_quote.inputSchema.products changed from unset to []. rev 12 → 13 · 28 d ago

Non-breaking 1 non-breaking change. Optional parameter merchant was added at search_catalog.inputSchema. rev 11 → 12 · 39 d ago

Non-breaking 25 non-breaking changes. Output field cited_field_count was added at get_product.outputSchema.product. rev 10 → 11 · 40 d ago

Non-breaking 1 non-breaking change. Output field related_products was added at get_product.outputSchema. rev 9 → 10 · 77 d ago

Non-breaking 2 non-breaking changes. Output field live_discovery was added at find_products.outputSchema. rev 8 → 9 · 82 d ago

Non-breaking 1 non-breaking change. Output field accepted_defaults was added at research_shopping.outputSchema. rev 7 → 8 · 84 d ago

Non-breaking 2 non-breaking changes. Output field reason was added at search_catalog.outputSchema. rev 6 → 7 · 84 d ago

Breaking 1 breaking change. minLength at search_catalog.inputSchema.q was set to 0. rev 5 → 6 · 85 d ago

Non-breaking 1 non-breaking change. find_products.outputSchema.status now also accepts refused. rev 4 → 5 · 85 d ago

Non-breaking 1 non-breaking change. Output field reason was added at find_products.outputSchema. rev 3 → 4 · 85 d ago

Non-breaking 2 non-breaking changes. find_products.outputSchema.status now also accepts no_match. rev 2 → 3 · 87 d ago

Non-breaking 1 non-breaking change. Optional parameter persona was added at research_shopping.inputSchema. rev 1 → 2 · 88 d ago

Full snapshots are stored only when the canonical hash changes — unchanged observations update freshness without duplicating the contract.

Recent observations latest 30

Observed	Result	Latency
Nov 2, 2026 — 12:55 AM (2 h ago)	Reachable	490 ms
Nov 1, 2026 — 10:50 PM (4 h ago)	Reachable	611 ms
Nov 1, 2026 — 8:45 PM (6 h ago)	Reachable	464 ms
Nov 1, 2026 — 6:40 PM (8 h ago)	Reachable	434 ms
Nov 1, 2026 — 4:35 PM (10 h ago)	Reachable	407 ms
Nov 1, 2026 — 2:30 PM (12 h ago)	Reachable	450 ms
Nov 1, 2026 — 12:25 PM (14 h ago)	Reachable	379 ms
Nov 1, 2026 — 10:20 AM (16 h ago)	Reachable	469 ms
Nov 1, 2026 — 8:15 AM (18 h ago)	Reachable	459 ms
Nov 1, 2026 — 6:10 AM (20 h ago)	Reachable	379 ms
Nov 1, 2026 — 4:05 AM (22 h ago)	Reachable	452 ms
Nov 1, 2026 — 2:00 AM (1 d ago)	Reachable	500 ms
Oct 31, 2026 — 11:55 PM (1 d ago)	Reachable	539 ms
Oct 31, 2026 — 9:50 PM (1 d ago)	Reachable	487 ms
Oct 31, 2026 — 7:45 PM (1 d ago)	Reachable	532 ms
Oct 31, 2026 — 5:40 PM (1 d ago)	Reachable	461 ms
Oct 31, 2026 — 3:35 PM (1 d ago)	Reachable	434 ms
Oct 31, 2026 — 1:30 PM (2 d ago)	Reachable	450 ms
Oct 31, 2026 — 11:25 AM (2 d ago)	Reachable	443 ms
Oct 31, 2026 — 9:20 AM (2 d ago)	Reachable	410 ms
Oct 31, 2026 — 7:15 AM (2 d ago)	Reachable	541 ms
Oct 31, 2026 — 5:10 AM (2 d ago)	Reachable	410 ms
Oct 31, 2026 — 3:05 AM (2 d ago)	Reachable	422 ms
Oct 31, 2026 — 1:00 AM (2 d ago)	Reachable	489 ms
Oct 30, 2026 — 10:55 PM (2 d ago)	Reachable	517 ms
Oct 30, 2026 — 8:50 PM (2 d ago)	Reachable	479 ms
Oct 30, 2026 — 6:45 PM (2 d ago)	Reachable	457 ms
Oct 30, 2026 — 4:40 PM (2 d ago)	Reachable	491 ms
Oct 30, 2026 — 2:35 PM (2 d ago)	Reachable	480 ms
Oct 30, 2026 — 12:30 PM (3 d ago)	Reachable	540 ms

Latest check — evidence & validation Nov 2, 2026 — 12:55 AM

Reachable MCP Tools Edge Scanner ScheduledHTTP 200490 msStreamable HTTP2025-06-18

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "text/event-stream"
}

serverInfo — from initialize

{
  "name": "AirShelf",
  "version": "1.0.0",
  "title": null
}

Server name	`AirShelf`
Server version	`1.0.0`
Transport	Streamable HTTP
Protocol version	`2025-06-18`
First observed	Aug 6, 2026
Last observed	2 h ago
Last successful	2 h ago
Origin	Registry seed

AirShelf Catalog MCP · AirShelf

Availability — last 30 days

Advertised capabilities

Tools 8

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Input schema

Output schema

Resources 3

Prompts 0

Canonical contract hash

Revisions 13

Contract changes 12

Recent observations latest 30

Publisher supplied

Independently observed

Name	AirShelf Catalog MCP
Vendor	AirShelf
Category	other
Docs	—
Repository	—
Auth expected	Auth expectations unknown