Boolsai Signals MCP · Boolsai

Not responding as MCP

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

https://signals.boolsai.ai/mcp

Badge

Not responding as MCPHTTP 530 with content-type text/plain; charset=utf-8 — this does not look like an MCP endpoint.

Since Sep 27, 2026 — 4:00 AM (36 d ago)

0.0%

Availability · 30 days · 8 checks

67 ms

Latency (last observation)

rev 1

Contract

87days

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 1 d ago by MCP Tools Edge Scanner · scheduled every 120 min

Outage Sep 27, 2026 — 6:05 AM

HTTP 530 with content-type text/plain; charset=utf-8 — this does not look like an MCP endpoint.

VerifiedTwo consecutive observations failed (latest: not_mcp, HTTP 530).

InterpretationClients depending on this endpoint may currently be unable to connect.

Raw event details

{
  "result": "not_mcp",
  "error": "HTTP 530 with content-type text/plain; charset=utf-8 — this does not look like an MCP endpoint."
}

Observed by MCP Tools Edge Scanner

Recovery Sep 12, 2026 — 4:00 AM

Endpoint returned to service after 730 minutes.

VerifiedA successful observation followed a confirmed outage (result: reachable).

Observed by MCP Tools Edge Scanner 12 h 10 m

Outage Sep 11, 2026 — 5:51 PM

Rate limited (HTTP 429).

VerifiedTwo consecutive observations failed (latest: rate_limited, HTTP 429).

InterpretationClients depending on this endpoint may currently be unable to connect.

Raw event details

{
  "result": "rate_limited",
  "error": "Rate limited (HTTP 429)."
}

Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 4:55 AM

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

VerifiedCanonical contract hash sha256:746a71e649775aa6… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:746a71e649775aa64c555bf5cbbb10434ca902a189a0452c4960aaa8066f9186"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 12 Resources Prompts Logging Completions Experimental

Tools 12

universe_summary 0 params Orient the agent: total events, tickers, date range, top event types, top detectors, price coverage, SPY bench…

Orient the agent: total events, tickers, date range, top event types, top detectors, price coverage, SPY benchmark status. Call this FIRST when starting research. Returns counts that let the agent reason about sample sizes before drilling in.

Input schema

No parameters.

Raw schema JSON

universe_summary — raw

{
  "name": "universe_summary",
  "description": "Orient the agent: total events, tickers, date range, top event types, top detectors, price coverage, SPY benchmark status. Call this FIRST when starting research. Returns counts that let the agent reason about sample sizes before drilling in.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  }
}

find_signals 4 params Automated pattern discovery — scans event_type × detector × diff_field × severity combinations and returns tho…

Automated pattern discovery — scans event_type × detector × diff_field × severity combinations and returns those with the strongest forward-return characteristics (α vs SPY, % positive, n). Use this when you don't have a specific hypothesis yet. Returns sorted by α at +7D descending. Filter by min_n to set a sample-size floor.

Input schema

Parameter	Type	Description & constraints
min_n	integer	Minimum sample size (default 10) default: 10
horizon_days	integer	Forward-return window (default 7) default: 7
top_k	integer	Top K combos to return (default 15) default: 15
group_by	enum(5)	What dimension to slice on one of: "event_type", "detector", "diff_field", "severity", "co_occurrence" · default: "event_type"

Raw schema JSON

find_signals — raw

{
  "name": "find_signals",
  "description": "Automated pattern discovery — scans event_type × detector × diff_field × severity combinations and returns those with the strongest forward-return characteristics (α vs SPY, % positive, n). Use this when you don&#39;t have a specific hypothesis yet. Returns sorted by α at +7D descending. Filter by min_n to set a sample-size floor.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "min_n": {
        "type": "integer",
        "description": "Minimum sample size (default 10)",
        "default": 10
      },
      "horizon_days": {
        "type": "integer",
        "description": "Forward-return window (default 7)",
        "default": 7
      },
      "top_k": {
        "type": "integer",
        "description": "Top K combos to return (default 15)",
        "default": 15
      },
      "group_by": {
        "type": "string",
        "enum": [
          "event_type",
          "detector",
          "diff_field",
          "severity",
          "co_occurrence"
        ],
        "default": "event_type",
        "description": "What dimension to slice on"
      }
    }
  }
}

test_filter 7 params Compute α stats for an arbitrary filter expression. Use this to test a specific hypothesis (e.g. 'tier_count_c…

Compute α stats for an arbitrary filter expression. Use this to test a specific hypothesis (e.g. 'tier_count_changed on enterprise-SaaS tickers' or 'severity 5 events that happened on Mondays'). Returns n, mean/median raw and α returns at +1/+3/+7d, % positive, and the worst-loss trade.

Input schema

Parameter	Type	Description & constraints
event_type	string	e.g. 'TIER_COUNT_CHANGED' (case-insensitive)
detector	string	e.g. 'pricing_detector'
severity_min	integer	minimum severity (1-5)
ticker	string	single ticker to filter to
co_occurrence_min	integer	min same-day detector count (4 = 'real redesign')
since	string	YYYY-MM-DD lower bound
until	string	YYYY-MM-DD upper bound

Raw schema JSON

test_filter — raw

{
  "name": "test_filter",
  "description": "Compute α stats for an arbitrary filter expression. Use this to test a specific hypothesis (e.g. &#39;tier_count_changed on enterprise-SaaS tickers&#39; or &#39;severity 5 events that happened on Mondays&#39;). Returns n, mean/median raw and α returns at +1/+3/+7d, % positive, and the worst-loss trade.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "event_type": {
        "type": "string",
        "description": "e.g. &#39;TIER_COUNT_CHANGED&#39; (case-insensitive)"
      },
      "detector": {
        "type": "string",
        "description": "e.g. &#39;pricing_detector&#39;"
      },
      "severity_min": {
        "type": "integer",
        "description": "minimum severity (1-5)"
      },
      "ticker": {
        "type": "string",
        "description": "single ticker to filter to"
      },
      "co_occurrence_min": {
        "type": "integer",
        "description": "min same-day detector count (4 = &#39;real redesign&#39;)"
      },
      "since": {
        "type": "string",
        "description": "YYYY-MM-DD lower bound"
      },
      "until": {
        "type": "string",
        "description": "YYYY-MM-DD upper bound"
      }
    }
  }
}

recent_events 2 params Live signal feed: events fired in the last N days (default 7). Returns each event with the predicted α range b…

Live signal feed: events fired in the last N days (default 7). Returns each event with the predicted α range based on its event type's historical performance. Use this to surface 'what should I be looking at right now?'

Input schema

Parameter	Type	Description & constraints
days	integer	Lookback in calendar days (max 30) default: 7
min_co_occurrence	integer	Only show events with this many same-day detectors (4 = high-conviction)

Raw schema JSON

recent_events — raw

{
  "name": "recent_events",
  "description": "Live signal feed: events fired in the last N days (default 7). Returns each event with the predicted α range based on its event type&#39;s historical performance. Use this to surface &#39;what should I be looking at right now?&#39;",
  "inputSchema": {
    "type": "object",
    "properties": {
      "days": {
        "type": "integer",
        "default": 7,
        "description": "Lookback in calendar days (max 30)"
      },
      "min_co_occurrence": {
        "type": "integer",
        "description": "Only show events with this many same-day detectors (4 = high-conviction)"
      }
    }
  }
}

event_dossier 1 param · 1 required Deep dive on a single event: full diff (added/removed values), surrounding price action (-3D to +14D), predict…

Deep dive on a single event: full diff (added/removed values), surrounding price action (-3D to +14D), predicted vs actual α, links to wayback comparison. Use this to investigate a specific event flagged by find_signals or recent_events.

Input schema

Parameter	Type	Description & constraints
event_id*	integer	change_event id

Raw schema JSON

event_dossier — raw

{
  "name": "event_dossier",
  "description": "Deep dive on a single event: full diff (added/removed values), surrounding price action (-3D to +14D), predicted vs actual α, links to wayback comparison. Use this to investigate a specific event flagged by find_signals or recent_events.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "event_id": {
        "type": "integer",
        "description": "change_event id"
      }
    },
    "required": [
      "event_id"
    ]
  }
}

scan_at_date 2 params · 2 required Scan a URL as it appeared on a historical date via the Wayback Machine. Uses intel.boolsai.ai against the wayb…

Scan a URL as it appeared on a historical date via the Wayback Machine. Uses intel.boolsai.ai against the wayback-wrapped URL. Returns the same JSON shape as Boolsai Scan but for a historical snapshot. Use when investigating WHEN a vendor was added/removed.

Input schema

Parameter	Type	Description & constraints
url*	string	Original URL (e.g. 'https://gymshark.com/')
date*	string	YYYY-MM-DD — closest wayback snapshot on or before this date will be used

Raw schema JSON

scan_at_date — raw

{
  "name": "scan_at_date",
  "description": "Scan a URL as it appeared on a historical date via the Wayback Machine. Uses intel.boolsai.ai against the wayback-wrapped URL. Returns the same JSON shape as Boolsai Scan but for a historical snapshot. Use when investigating WHEN a vendor was added/removed.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "description": "Original URL (e.g. &#39;https://gymshark.com/&#39;)"
      },
      "date": {
        "type": "string",
        "description": "YYYY-MM-DD — closest wayback snapshot on or before this date will be used"
      }
    },
    "required": [
      "url",
      "date"
    ]
  }
}

ticker_history 2 params · 1 required All events fired on a single ticker, plus price action timeline. Use this to investigate one company's pattern…

All events fired on a single ticker, plus price action timeline. Use this to investigate one company's pattern (e.g. 'show me everything we caught on NFLX').

Input schema

Parameter	Type	Description & constraints
ticker*	string	e.g. 'NFLX'
limit	integer	— default: 50

Raw schema JSON

ticker_history — raw

{
  "name": "ticker_history",
  "description": "All events fired on a single ticker, plus price action timeline. Use this to investigate one company&#39;s pattern (e.g. &#39;show me everything we caught on NFLX&#39;).",
  "inputSchema": {
    "type": "object",
    "properties": {
      "ticker": {
        "type": "string",
        "description": "e.g. &#39;NFLX&#39;"
      },
      "limit": {
        "type": "integer",
        "default": 50
      }
    },
    "required": [
      "ticker"
    ]
  }
}

wayback_backtest 6 params Run an SPY-benchmarked backtest on the WAYBACK historical event dataset (2+ years, 13K events) instead of the …

Run an SPY-benchmarked backtest on the WAYBACK historical event dataset (2+ years, 13K events) instead of the recent live event dataset (2 months, 1.7K events). Much bigger samples for statistical confidence. Group by change_type / key_path / domain.

Input schema

Parameter	Type	Description & constraints
group_by	enum(5)	Dimension to slice on one of: "change_type", "key_path", "key_name", "parent_path", "domain" · default: "key_path"
min_n	integer	Minimum sample size default: 20
horizon_days	integer	Forward-return window default: 7
top_k	integer	— default: 15
since	string	YYYY-MM-DD lower bound on event date (default: when prices start)
exclude_noise	boolean	Filter out is_meta_noise=1 events default: true

Raw schema JSON

wayback_backtest — raw

{
  "name": "wayback_backtest",
  "description": "Run an SPY-benchmarked backtest on the WAYBACK historical event dataset (2+ years, 13K events) instead of the recent live event dataset (2 months, 1.7K events). Much bigger samples for statistical confidence. Group by change_type / key_path / domain.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "group_by": {
        "type": "string",
        "enum": [
          "change_type",
          "key_path",
          "key_name",
          "parent_path",
          "domain"
        ],
        "default": "key_path",
        "description": "Dimension to slice on"
      },
      "min_n": {
        "type": "integer",
        "default": 20,
        "description": "Minimum sample size"
      },
      "horizon_days": {
        "type": "integer",
        "default": 7,
        "description": "Forward-return window"
      },
      "top_k": {
        "type": "integer",
        "default": 15
      },
      "since": {
        "type": "string",
        "description": "YYYY-MM-DD lower bound on event date (default: when prices start)"
      },
      "exclude_noise": {
        "type": "boolean",
        "default": true,
        "description": "Filter out is_meta_noise=1 events"
      }
    }
  }
}

domain_timeline 4 params · 1 required Week-by-week wayback diff timeline for one domain. Returns every detected stack change (additions / removals) …

Week-by-week wayback diff timeline for one domain. Returns every detected stack change (additions / removals) with week date. Use this to see when a vendor was added/removed historically, e.g. 'when did adobe.com add Segment?'

Input schema

Parameter	Type	Description & constraints
domain*	string	e.g. 'adobe.com'
change_type	enum(4)	— one of: "added", "removed", "changed", "any" · default: "any"
contains	string	Filter to events whose key_path or key_name contains this string (e.g. 'segment')
limit	integer	— default: 100

Raw schema JSON

domain_timeline — raw

{
  "name": "domain_timeline",
  "description": "Week-by-week wayback diff timeline for one domain. Returns every detected stack change (additions / removals) with week date. Use this to see when a vendor was added/removed historically, e.g. &#39;when did adobe.com add Segment?&#39;",
  "inputSchema": {
    "type": "object",
    "properties": {
      "domain": {
        "type": "string",
        "description": "e.g. &#39;adobe.com&#39;"
      },
      "change_type": {
        "type": "string",
        "enum": [
          "added",
          "removed",
          "changed",
          "any"
        ],
        "default": "any"
      },
      "contains": {
        "type": "string",
        "description": "Filter to events whose key_path or key_name contains this string (e.g. &#39;segment&#39;)"
      },
      "limit": {
        "type": "integer",
        "default": 100
      }
    },
    "required": [
      "domain"
    ]
  }
}

signal_landscape 5 params ONE-SHOT cross-signal sweep. Computes α-vs-SPY stats simultaneously across event_type, detector, diff_field, s…

ONE-SHOT cross-signal sweep. Computes α-vs-SPY stats simultaneously across event_type, detector, diff_field, severity, AND co_occurrence dimensions — returns the full landscape in a single response. Use this FIRST when you want to see where signal lives without having to call find_signals N times. Stateless, pure D1, no rate-limit risk, ~1s response. Cached per arg set for sub-100ms repeated queries.

Input schema

Parameter	Type	Description & constraints
source	enum(3)	Which event dataset to scan. 'live' = 1.7K recent. 'wayback' = 13K over 2 years. 'both' = run both and return side-by-side. one of: "live", "wayback", "both" · default: "both"
horizon_days	integer	Forward-return window (default 7) default: 7
min_n	integer	Sample-size floor per group default: 20
top_k_per_dim	integer	Top K results per dimension (default 8) default: 8
since	string	Optional YYYY-MM-DD lower bound on event date

Raw schema JSON

signal_landscape — raw

{
  "name": "signal_landscape",
  "description": "ONE-SHOT cross-signal sweep. Computes α-vs-SPY stats simultaneously across event_type, detector, diff_field, severity, AND co_occurrence dimensions — returns the full landscape in a single response. Use this FIRST when you want to see where signal lives without having to call find_signals N times. Stateless, pure D1, no rate-limit risk, ~1s response. Cached per arg set for sub-100ms repeated queries.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "source": {
        "type": "string",
        "enum": [
          "live",
          "wayback",
          "both"
        ],
        "default": "both",
        "description": "Which event dataset to scan. &#39;live&#39; = 1.7K recent. &#39;wayback&#39; = 13K over 2 years. &#39;both&#39; = run both and return side-by-side."
      },
      "horizon_days": {
        "type": "integer",
        "default": 7,
        "description": "Forward-return window (default 7)"
      },
      "min_n": {
        "type": "integer",
        "default": 20,
        "description": "Sample-size floor per group"
      },
      "top_k_per_dim": {
        "type": "integer",
        "default": 8,
        "description": "Top K results per dimension (default 8)"
      },
      "since": {
        "type": "string",
        "description": "Optional YYYY-MM-DD lower bound on event date"
      }
    }
  }
}

signal_diff 3 params · 2 required Compare two signal patterns side-by-side. e.g. 'how does PRICING_TIERS_ADDED compare to VENDORS_DETECTED_CHANG…

Compare two signal patterns side-by-side. e.g. 'how does PRICING_TIERS_ADDED compare to VENDORS_DETECTED_CHANGED on the live dataset?' Returns α, %pos, sample size, worst/best trades for each, plus delta. Pure D1, fast.

Input schema

Parameter	Type	Description & constraints
signal_a*	object	First filter (same shape as test_filter args)
signal_b*	object	Second filter
horizon_days	integer	— default: 7

Raw schema JSON

signal_diff — raw

{
  "name": "signal_diff",
  "description": "Compare two signal patterns side-by-side. e.g. &#39;how does PRICING_TIERS_ADDED compare to VENDORS_DETECTED_CHANGED on the live dataset?&#39; Returns α, %pos, sample size, worst/best trades for each, plus delta. Pure D1, fast.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "signal_a": {
        "type": "object",
        "description": "First filter (same shape as test_filter args)"
      },
      "signal_b": {
        "type": "object",
        "description": "Second filter"
      },
      "horizon_days": {
        "type": "integer",
        "default": 7
      }
    },
    "required": [
      "signal_a",
      "signal_b"
    ]
  }
}

farm_domain 3 params · 1 required Bulk-farm a domain's historical wayback snapshots into our index. Use this when you need backtest history on a…

Bulk-farm a domain's historical wayback snapshots into our index. Use this when you need backtest history on a domain we haven't already farmed (i.e. wayback_backtest / domain_timeline return no data for it). Hits CDX → samples weekly → parallel-scans up to 50 snapshots via intel.boolsai.ai → inserts into wayback_intel_profiles. After farming completes you can call wayback_backtest or domain_timeline on the domain immediately. Cost: ~30-60s wall time, ~50 intel scans.

Input schema

Parameter	Type	Description & constraints
domain*	string	Bare domain, e.g. 'sweetgreen.com'
weeks	integer	How many weeks of history to farm (default 26 = ~6 months; max 100) default: 26
max_snapshots	integer	Hard cap on snapshots to fetch (default 50; max 200) default: 50

Raw schema JSON

farm_domain — raw

{
  "name": "farm_domain",
  "description": "Bulk-farm a domain&#39;s historical wayback snapshots into our index. Use this when you need backtest history on a domain we haven&#39;t already farmed (i.e. wayback_backtest / domain_timeline return no data for it). Hits CDX → samples weekly → parallel-scans up to 50 snapshots via intel.boolsai.ai → inserts into wayback_intel_profiles. After farming completes you can call wayback_backtest or domain_timeline on the domain immediately. Cost: ~30-60s wall time, ~50 intel scans.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "domain": {
        "type": "string",
        "description": "Bare domain, e.g. &#39;sweetgreen.com&#39;"
      },
      "weeks": {
        "type": "integer",
        "default": 26,
        "description": "How many weeks of history to farm (default 26 = ~6 months; max 100)"
      },
      "max_snapshots": {
        "type": "integer",
        "default": 50,
        "description": "Hard cap on snapshots to fetch (default 50; max 200)"
      }
    },
    "required": [
      "domain"
    ]
  }
}

Resources 0

No resources advertised.

Prompts 0

No prompts advertised.

Inventory recorded Aug 6, 2026 — 4:55 AM as rev 1. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 1

sha256:746a71e649775aa64c555bf5cbbb10434ca902a189a0452c4960aaa8066f9186

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 1

Rev	Observed	Hash
rev 1 baseline	Aug 6, 2026 — 4:55 AM (88 d ago)

Contract changes 0

No drift observed — every successful observation since Aug 6, 2026 has matched the baseline hash. Boring, in the best way.

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

Recent observations latest 8

Observed	Result	Latency
Oct 31, 2026 — 5:05 PM (1 d ago)	Not an MCP response	67 ms
Oct 27, 2026 — 5:00 PM (5 d ago)	Not an MCP response	46 ms
Oct 23, 2026 — 4:55 PM (9 d ago)	Not an MCP response	93 ms
Oct 19, 2026 — 4:50 PM (13 d ago)	Not an MCP response	100 ms
Oct 15, 2026 — 4:45 PM (17 d ago)	Not an MCP response	100 ms
Oct 11, 2026 — 4:40 PM (21 d ago)	Not an MCP response	46 ms
Oct 7, 2026 — 4:35 PM (25 d ago)	Not an MCP response	33 ms
Oct 3, 2026 — 4:35 PM (29 d ago)	Not an MCP response	27 ms

Latest check — evidence & validation Oct 31, 2026 — 5:05 PM

Not an MCP response MCP Tools Edge Scanner ScheduledHTTP 53067 ms

Error detailHTTP 530 with content-type text/plain; charset=utf-8 — this does not look like an MCP endpoint.

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "text/plain; charset=UTF-8"
}

response body — first bytes

error code: 1016

Baseline capturedThe current contract is rev 1 — the reference state for this endpoint. Future observations will identify outages, recoveries, protocol changes, and contract drift from this state.

Server name	`boolsai-signals`
Server version	`1.0.0`
Transport	Streamable HTTP
Protocol version	`2025-06-18`
First observed	Aug 6, 2026
Last observed	1 d ago
Last successful	36 d ago
Origin	Registry seed

Boolsai Signals MCP · Boolsai

Availability — last 30 days

Advertised capabilities

Tools 12

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Input schema

Resources 0

Prompts 0

Canonical contract hash

Revisions 1

Contract changes 0

Recent observations latest 8

Publisher supplied

Independently observed

Name	Boolsai Signals MCP
Vendor	Boolsai
Category	data
Docs	—
Repository	—
Auth expected	Auth expectations unknown