Arclan MCP Registry

ai.arclan/registry

This is a registry and monitoring system for MCP servers themselves rather than a connector to an external service. It validates other MCP servers through live handshakes, assigns reliability scores, and provides continuous monitoring. You'd use this when you need to discover available MCP servers, check their health status, or verify they're actually responding before integrating them into your workflow. Think of it as a health check and directory service for the MCP ecosystem. The streamable HTTP transport suggests you can query the registry programmatically to get real-time status on which servers are up and performing well.

tools: 4
transport: HTTP
last updated: Sep 12, 2026

Open website

Install

From registry metadata

$ npx add-mcp https://arclan.ai/mcp --name registry

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http registry https://arclan.ai/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 4 tools

Verified live against the running server on Nov 6, 2026.

query_registrySearch 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...7 params

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...

Parameters* required

capabilitystring

Filter by tool name or keyword (searches name, description, tools)

limitnumber

Max results to return 1–20 (default 10)

min_scorenumber

Minimum validation score 0–100 (default 0)

production_safeboolean

Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters.

read_onlyboolean

Only return servers with no write or exec tools — safe for read-only agent workflows.

statusstring

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

transportstring

Filter by transport typeone of http · sse · stdio · unknown

get_serverGet 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.2 params

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.

Parameters* required

idstring

Server name, registry ID slug, or any identifier (e.g. "github", "brave-search", "gateway-pipeworx-io-rpc-mcp")

urlstring

The MCP server endpoint URL (e.g. "https://mcp.example.com/mcp")

recommend_serverGet 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...5 params

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...

Parameters* required

authboolean

Include servers that require authentication (default: true)

limitnumber

Max results 1–20 (default: 5)

production_safeboolean

Only return production-safe servers (uptime > 97%, handshake > 95%)

qstring

Task or capability query — e.g. "search the web" or "read files"

read_onlyboolean

Only return servers with no write-classified tools

report_serverSubmit 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 +...14 params

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 +...

Parameters* required

agentIdstring

Identifier for the reporting agent (optional)

componentScorenumber

Score 0–100 for the specified criterion

criterionstring

Specific reliability criterion being scored (enables structured component scoring)one of output_reliability · side_effect_transparency · failure_handling · rate_limits · agent_feedback

environmentstring

Environment the server was used inone of prod · staging · dev · unknown

errorsarray

Array of error strings encountered during tool use

evidenceRefstring

Trace ID, log URL, or other reference supporting this report

latencyMsnumber

Total wall-clock latency in milliseconds

outcome*string

Result of using the serverone of success · failure · partial

serverUrl*string

The MCP server endpoint URL that was used

severitystring

Severity of the worst issue encounteredone of info · warning · error · critical

taskCategorystring

Category of task attempted (e.g. "search", "write", "read")

taskDescriptionstring

Brief description of what the task was

toolsUsedarray

List of tool names that were called

turnsRequirednumber

Number of turns to complete the task

Details

Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026