Arclan MCP Registry · Arclan

Operational

Unclaimed — claim this pagedeveloper-tools Streamable HTTP2024-11-05 Auth expectations unknown

https://arclan.ai/mcp

Badge

92.3%

Availability · 30 days · 349 checks

398 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 2 h ago by MCP Tools Edge Scanner · scheduled every 120 min

Recovery Oct 31, 2026 — 7:00 AM

Endpoint returned to service after 250 minutes.

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

Observed by MCP Tools Edge Scanner 4 h 10 m

Outage Oct 31, 2026 — 4:55 AM

HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint.

VerifiedTwo consecutive observations failed (latest: not_mcp, HTTP 500).

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

Raw event details

{
  "result": "not_mcp",
  "error": "HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint."
}

Observed by MCP Tools Edge Scanner

Recovery Oct 31, 2026 — 12:45 AM

Endpoint returned to service after 250 minutes.

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

Observed by MCP Tools Edge Scanner 4 h 10 m

Outage Oct 30, 2026 — 10:40 PM

HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint.

VerifiedTwo consecutive observations failed (latest: not_mcp, HTTP 500).

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

Raw event details

{
  "result": "not_mcp",
  "error": "HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint."
}

Observed by MCP Tools Edge Scanner

Recovery Oct 24, 2026 — 9:40 PM

Endpoint returned to service after 250 minutes.

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

Observed by MCP Tools Edge Scanner 4 h 10 m

Outage Oct 24, 2026 — 7:35 PM

HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint.

VerifiedTwo consecutive observations failed (latest: not_mcp, HTTP 500).

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

Raw event details

{
  "result": "not_mcp",
  "error": "HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint."
}

Observed by MCP Tools Edge Scanner

Recovery Oct 18, 2026 — 8:25 PM

Endpoint returned to service after 250 minutes.

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

Observed by MCP Tools Edge Scanner 4 h 10 m

Outage Oct 18, 2026 — 6:20 PM

HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint.

VerifiedTwo consecutive observations failed (latest: not_mcp, HTTP 500).

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

Raw event details

{
  "result": "not_mcp",
  "error": "HTTP 500 with content-type text/html; charset=iso-8859-1 — this does not look like an MCP endpoint."
}

Observed by MCP Tools Edge Scanner

Recovery Aug 18, 2026 — 6:46 AM

Endpoint returned to service after 250 minutes.

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

Observed by MCP Tools Edge Scanner 4 h 10 m

Outage — initialization timed out Aug 18, 2026 — 4:41 AM

No response within 10 seconds.

VerifiedTwo consecutive observations failed (latest: timeout).

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

Raw event details

{
  "result": "timeout",
  "error": "No response within 10 seconds."
}

Observed by MCP Tools Edge Scanner

Baseline captured Aug 6, 2026 — 5:05 AM

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

VerifiedCanonical contract hash sha256:7a583ad7889f1914… computed from the normalized capability inventory.

Raw event details

{
  "contractHash": "sha256:7a583ad7889f1914e2c08eaf55a1eaddd889e13a3666cf5648f36beb08c8b2ae"
}

Observed by MCP Tools Edge Scanner

Advertised capabilities

Tools · 4 Resources Prompts Logging Completions Experimental

Tools 4

query_registry 7 params Search the Arclan registry for MCP servers. By default returns only connectable servers (active, mcp_partial, …

Search the Arclan registry for MCP servers. By default returns only connectable servers (active, mcp_partial, auth_gated). Use status=stdio to browse local-only servers available for installation. Use status=all to query the full index. Use production_safe=true to restrict to servers with uptime > 97% and handshake success > 95%. Use read_only=true to restrict to servers with no write or exec tools. Use this before connecting to an MCP server to check its validation status and score. After using a server, call report_server to contribute reliability data.

Input schema

Parameter	Type	Description & constraints
capability	string	Filter by tool name or keyword (searches name, description, tools)
min_score	number	Minimum validation score 0–100 (default 0)
transport	enum(4)	Filter by transport type one of: "http", "sse", "stdio", "unknown"
status	enum(8)	Filter by state. Default (omit): connectable states only (active + mcp_partial + auth_gated). Use "stdio" for local-install catalog. Use "all" for the full index. one of: "active", "mcp_partial", "auth_gated", "stdio", "unreachable", "invalid", "zombie", "all"
production_safe	boolean	Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters.
read_only	boolean	Only return servers with no write or exec tools — safe for read-only agent workflows.
limit	number	Max results to return 1–20 (default 10)

Raw schema JSON

query_registry — raw

{
  "name": "query_registry",
  "description": "Search the Arclan registry for MCP servers. By default returns only connectable servers (active, mcp_partial, auth_gated). Use status=stdio to browse local-only servers available for installation. Use status=all to query the full index. Use production_safe=true to restrict to servers with uptime > 97% and handshake success > 95%. Use read_only=true to restrict to servers with no write or exec tools. Use this before connecting to an MCP server to check its validation status and score. After using a server, call report_server to contribute reliability data.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "capability": {
        "type": "string",
        "description": "Filter by tool name or keyword (searches name, description, tools)"
      },
      "min_score": {
        "type": "number",
        "description": "Minimum validation score 0–100 (default 0)"
      },
      "transport": {
        "type": "string",
        "enum": [
          "http",
          "sse",
          "stdio",
          "unknown"
        ],
        "description": "Filter by transport type"
      },
      "status": {
        "type": "string",
        "enum": [
          "active",
          "mcp_partial",
          "auth_gated",
          "stdio",
          "unreachable",
          "invalid",
          "zombie",
          "all"
        ],
        "description": "Filter by state. Default (omit): connectable states only (active + mcp_partial + auth_gated). Use \"stdio\" for local-install catalog. Use \"all\" for the full index."
      },
      "production_safe": {
        "type": "boolean",
        "description": "Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters."
      },
      "read_only": {
        "type": "boolean",
        "description": "Only return servers with no write or exec tools — safe for read-only agent workflows."
      },
      "limit": {
        "type": "number",
        "description": "Max results to return 1–20 (default 10)"
      }
    }
  }
}

get_server 2 params Get full details for a specific MCP server. Pass the server name (e.g. "GitHub", "Brave Search"), registry ID …

Get full details for a specific MCP server. Pass the server name (e.g. "GitHub", "Brave Search"), registry ID slug, or endpoint URL. Returns score, state, tools list, latency, and recent test history.

Input schema

Parameter	Type	Description & constraints
url	string	The MCP server endpoint URL (e.g. "https://mcp.example.com/mcp")
id	string	Server name, registry ID slug, or any identifier (e.g. "github", "brave-search", "gateway-pipeworx-io-rpc-mcp")

Raw schema JSON

get_server — raw

{
  "name": "get_server",
  "description": "Get full details for a specific MCP server. Pass the server name (e.g. \"GitHub\", \"Brave Search\"), registry ID slug, or endpoint URL. Returns score, state, tools list, latency, and recent test history.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "url": {
        "type": "string",
        "description": "The MCP server endpoint URL (e.g. \"https://mcp.example.com/mcp\")"
      },
      "id": {
        "type": "string",
        "description": "Server name, registry ID slug, or any identifier (e.g. \"github\", \"brave-search\", \"gateway-pipeworx-io-rpc-mcp\")"
      }
    }
  }
}

recommend_server 5 params Get ranked MCP server recommendations for a task. Returns servers scored by production safety, keyword relevan…

Get ranked MCP server recommendations for a task. Returns servers scored by production safety, keyword relevance, registry score, latency, and freshness. Each result includes a reason code array explaining why it was ranked. Use this instead of query_registry when you want an opinionated ranked list rather than a filtered search.

Input schema

Parameter	Type	Description & constraints
q	string	Task or capability query — e.g. "search the web" or "read files"
auth	boolean	Include servers that require authentication (default: true)
production_safe	boolean	Only return production-safe servers (uptime > 97%, handshake > 95%)
read_only	boolean	Only return servers with no write-classified tools
limit	number	Max results 1–20 (default: 5)

Raw schema JSON

recommend_server — raw

{
  "name": "recommend_server",
  "description": "Get ranked MCP server recommendations for a task. Returns servers scored by production safety, keyword relevance, registry score, latency, and freshness. Each result includes a reason code array explaining why it was ranked. Use this instead of query_registry when you want an opinionated ranked list rather than a filtered search.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "q": {
        "type": "string",
        "description": "Task or capability query — e.g. \"search the web\" or \"read files\""
      },
      "auth": {
        "type": "boolean",
        "description": "Include servers that require authentication (default: true)"
      },
      "production_safe": {
        "type": "boolean",
        "description": "Only return production-safe servers (uptime > 97%, handshake > 95%)"
      },
      "read_only": {
        "type": "boolean",
        "description": "Only return servers with no write-classified tools"
      },
      "limit": {
        "type": "number",
        "description": "Max results 1–20 (default: 5)"
      }
    }
  }
}

report_server 14 params · 2 required Submit an agent usage report for an MCP server. Reports are aggregated and influence registry trust scores. Ca…

Submit an agent usage report for an MCP server. Reports are aggregated and influence registry trust scores. Call this after using an MCP server so the registry can track real-world reliability. Supports both a simple outcome report and a structured scoring report (criterion + component_score).

Input schema

Parameter	Type	Description & constraints
serverUrl*	string	The MCP server endpoint URL that was used
outcome*	enum(3)	Result of using the server one of: "success", "failure", "partial"
agentId	string	Identifier for the reporting agent (optional)
toolsUsed	array<string>	List of tool names that were called
turnsRequired	number	Number of turns to complete the task
latencyMs	number	Total wall-clock latency in milliseconds
taskCategory	string	Category of task attempted (e.g. "search", "write", "read")
taskDescription	string	Brief description of what the task was
errors	array<string>	Array of error strings encountered during tool use
criterion	enum(5)	Specific reliability criterion being scored (enables structured component scoring) one of: "output_reliability", "side_effect_transparency", "failure_handling", "rate_limits", "agent_feedback"
componentScore	number	Score 0–100 for the specified criterion
severity	enum(4)	Severity of the worst issue encountered one of: "info", "warning", "error", "critical"
environment	enum(4)	Environment the server was used in one of: "prod", "staging", "dev", "unknown"
evidenceRef	string	Trace ID, log URL, or other reference supporting this report

Raw schema JSON

report_server — raw

{
  "name": "report_server",
  "description": "Submit an agent usage report for an MCP server. Reports are aggregated and influence registry trust scores. Call this after using an MCP server so the registry can track real-world reliability. Supports both a simple outcome report and a structured scoring report (criterion + component_score).",
  "inputSchema": {
    "type": "object",
    "required": [
      "serverUrl",
      "outcome"
    ],
    "properties": {
      "serverUrl": {
        "type": "string",
        "description": "The MCP server endpoint URL that was used"
      },
      "outcome": {
        "type": "string",
        "enum": [
          "success",
          "failure",
          "partial"
        ],
        "description": "Result of using the server"
      },
      "agentId": {
        "type": "string",
        "description": "Identifier for the reporting agent (optional)"
      },
      "toolsUsed": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "List of tool names that were called"
      },
      "turnsRequired": {
        "type": "number",
        "description": "Number of turns to complete the task"
      },
      "latencyMs": {
        "type": "number",
        "description": "Total wall-clock latency in milliseconds"
      },
      "taskCategory": {
        "type": "string",
        "description": "Category of task attempted (e.g. \"search\", \"write\", \"read\")"
      },
      "taskDescription": {
        "type": "string",
        "description": "Brief description of what the task was"
      },
      "errors": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Array of error strings encountered during tool use"
      },
      "criterion": {
        "type": "string",
        "enum": [
          "output_reliability",
          "side_effect_transparency",
          "failure_handling",
          "rate_limits",
          "agent_feedback"
        ],
        "description": "Specific reliability criterion being scored (enables structured component scoring)"
      },
      "componentScore": {
        "type": "number",
        "description": "Score 0–100 for the specified criterion"
      },
      "severity": {
        "type": "string",
        "enum": [
          "info",
          "warning",
          "error",
          "critical"
        ],
        "description": "Severity of the worst issue encountered"
      },
      "environment": {
        "type": "string",
        "enum": [
          "prod",
          "staging",
          "dev",
          "unknown"
        ],
        "description": "Environment the server was used in"
      },
      "evidenceRef": {
        "type": "string",
        "description": "Trace ID, log URL, or other reference supporting this report"
      }
    }
  }
}

Resources 0

No resources advertised.

Prompts 0

No prompts advertised.

Inventory recorded Aug 6, 2026 — 5:05 AM as rev 1. Listing calls only — tools are never invoked.

Canonical contract hash

contract hash — rev 1

sha256:7a583ad7889f1914e2c08eaf55a1eaddd889e13a3666cf5648f36beb08c8b2ae

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 — 5:05 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 30

Observed	Result	Latency
Nov 2, 2026 — 12:40 AM (2 h ago)	Reachable	398 ms
Nov 1, 2026 — 10:35 PM (4 h ago)	Reachable	418 ms
Nov 1, 2026 — 8:30 PM (6 h ago)	Reachable	409 ms
Nov 1, 2026 — 6:25 PM (8 h ago)	Reachable	425 ms
Nov 1, 2026 — 4:20 PM (10 h ago)	Reachable	465 ms
Nov 1, 2026 — 2:15 PM (12 h ago)	Reachable	418 ms
Nov 1, 2026 — 12:10 PM (14 h ago)	Reachable	8850 ms
Nov 1, 2026 — 10:05 AM (16 h ago)	Reachable	442 ms
Nov 1, 2026 — 8:00 AM (18 h ago)	Timeout	10.0 s
Nov 1, 2026 — 5:55 AM (21 h ago)	Reachable	535 ms
Nov 1, 2026 — 3:50 AM (23 h ago)	Reachable	1393 ms
Nov 1, 2026 — 1:45 AM (1 d ago)	Reachable	414 ms
Oct 31, 2026 — 11:40 PM (1 d ago)	Reachable	404 ms
Oct 31, 2026 — 9:35 PM (1 d ago)	Reachable	443 ms
Oct 31, 2026 — 7:30 PM (1 d ago)	Reachable	539 ms
Oct 31, 2026 — 5:25 PM (1 d ago)	Reachable	419 ms
Oct 31, 2026 — 3:20 PM (1 d ago)	Not an MCP response	444 ms
Oct 31, 2026 — 1:15 PM (2 d ago)	Reachable	455 ms
Oct 31, 2026 — 11:10 AM (2 d ago)	Reachable	468 ms
Oct 31, 2026 — 9:05 AM (2 d ago)	Reachable	427 ms
Oct 31, 2026 — 7:00 AM (2 d ago)	Reachable	381 ms
Oct 31, 2026 — 4:55 AM (2 d ago)	Not an MCP response	9443 ms
Oct 31, 2026 — 2:50 AM (2 d ago)	Not an MCP response	5792 ms
Oct 31, 2026 — 12:45 AM (2 d ago)	Reachable	446 ms
Oct 30, 2026 — 10:40 PM (2 d ago)	Not an MCP response	3652 ms
Oct 30, 2026 — 8:35 PM (2 d ago)	Timeout	10.0 s
Oct 30, 2026 — 6:30 PM (2 d ago)	Reachable	416 ms
Oct 30, 2026 — 4:25 PM (2 d ago)	Reachable	412 ms
Oct 30, 2026 — 2:20 PM (3 d ago)	Reachable	511 ms
Oct 30, 2026 — 12:15 PM (3 d ago)	Reachable	513 ms

Latest check — evidence & validation Nov 2, 2026 — 12:40 AM

Reachable MCP Tools Edge Scanner ScheduledHTTP 200398 msStreamable HTTP2024-11-05

response headers (as observed)

{
  "server": "cloudflare",
  "content-type": "application/json; charset=utf-8"
}

serverInfo — from initialize

{
  "name": "arclan-registry",
  "version": "0.1.0",
  "title": null
}

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	`arclan-registry`
Server version	`0.1.0`
Transport	Streamable HTTP
Protocol version	`2024-11-05`
First observed	Aug 6, 2026
Last observed	2 h ago
Last successful	2 h ago
Origin	Registry seed

Arclan MCP Registry · Arclan

Availability — last 30 days

Advertised capabilities

Tools 4

Input schema

Input schema

Input schema

Input schema

Resources 0

Prompts 0

Canonical contract hash

Revisions 1

Contract changes 0

Recent observations latest 30

Publisher supplied

Independently observed

Name	Arclan MCP Registry
Vendor	Arclan
Category	developer-tools
Docs	—
Repository	—
Auth expected	Auth expectations unknown