arclan-registry
Registry code: 567bc1157b7cdfbc
MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.
from a public catalogue that lists it, not from the operator
- endpoint
- https://arclan.ai/mcp
- protocol
- streamable-http ·2024-11-05
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is arclan-registry live?
- Yes — it answered the hub's last check (checked 3h ago). It answered 98% of checks over the last 30 days.
- Is arclan-registry free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does arclan-registry have?
- 6 tools: recommend_server, sign_in, report_server, complete_sign_in, query_registry, get_server.
- Is arclan-registry safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 97.6%· all time 97.9%
last good check
of 6 tools
- degraded → live
- live → degraded· HTTP 502
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- used for
- search a registry of mcp servers
- get mcp server recommendations for a task
- report mcp server reliability
- takes → gives
- text → data
- tools
- 3 reads1 changes data
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
query_registry reads open 21h ago
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.
{ "type": "object", "properties": { "limit": { "type": "number", "description": "Max results to return 1–20 (default 10)" }, "status": { "enum": [ "active", "mcp_partial", "auth_gated", "stdio", "unreachable", "invalid", "zombie", "all" ], "type": "string", "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." }, "min_score": { "type": "number", "description": "Minimum validation score 0–100 (default 0)" }, "read_only": { "type": "boolean", "description": "Only return servers with no write or exec tools — safe for read-only agent workflows." }, "transport": { "enum": [ "http", "sse", "stdio", "unknown" ], "type": "string", "description": "Filter by transport type" }, "capability": { "type": "string", "description": "Filter by tool name or keyword (searches name, description, tools)" }, "production_safe": { "type": "boolean", "description": "Only return servers with uptime_7d > 97% and handshake_success_rate > 95%. Use when reliability matters." } } }arguments 49 linesget_server reads open 21h ago
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.
{ "type": "object", "properties": { "id": { "type": "string", "description": "Server name, registry ID slug, or any identifier (e.g. \"github\", \"brave-search\", \"gateway-pipeworx-io-rpc-mcp\")" }, "url": { "type": "string", "description": "The MCP server endpoint URL (e.g. \"https://mcp.example.com/mcp\")" } } }arguments 13 linesrecommend_server reads unknown never probed
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.
{ "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)" }, "limit": { "type": "number", "description": "Max results 1–20 (default: 5)" }, "read_only": { "type": "boolean", "description": "Only return servers with no write-classified tools" }, "production_safe": { "type": "boolean", "description": "Only return production-safe servers (uptime > 97%, handshake > 95%)" } } }arguments 25 linessign_in unknown never probed
Start GitHub sign-in to get an Arclan API key, without leaving MCP (OAuth device flow). Returns a verification URL and a short user_code — show both to the user and ask them to authorize in a browser. Then call complete_sign_in with the returned device_code to mint the key. A key raises your MCP rate limit above the keyless tier and tracks your usage.
{ "type": "object", "properties": {} }arguments 4 linesreport_server changes data unknown never probed
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).
{ "type": "object", "required": [ "serverUrl", "outcome" ], "properties": { "errors": { "type": "array", "items": { "type": "string" }, "description": "Array of error strings encountered during tool use" }, "agentId": { "type": "string", "description": "Identifier for the reporting agent (optional)" }, "outcome": { "enum": [ "success", "failure", "partial" ], "type": "string", "description": "Result of using the server" }, "severity": { "enum": [ "info", "warning", "error", "critical" ], "type": "string", "description": "Severity of the worst issue encountered" }, "criterion": { "enum": [ "output_reliability", "side_effect_transparency", "failure_handling", "rate_limits", "agent_feedback" ], "type": "string", "description": "Specific reliability criterion being scored (enables structured component scoring)" }, "latencyMs": { "type": "number", "description": "Total wall-clock latency in milliseconds" }, "serverUrl": { "type": "string", "description": "The MCP server endpoint URL that was used" }, "toolsUsed": { "type": "array", "items": { "type": "string" }, "description": "List of tool names that were called" }, "environment": { "enum": [ "prod", "staging", "dev", "unknown" ], "type": "string", "description": "Environment the server was used in" }, "evidenceRef": { "type": "string", "description": "Trace ID, log URL, or other reference supporting this report" }, "taskCategory": { "type": "string", "description": "Category of task attempted (e.g. \"search\", \"write\", \"read\")" }, "turnsRequired": { "type": "number", "description": "Number of turns to complete the task" }, "componentScore": { "type": "number", "description": "Score 0–100 for the specified criterion" }, "taskDescription": { "type": "string", "description": "Brief description of what the task was" } } }arguments 95 linescomplete_sign_in unknown never probed
Finish the GitHub sign-in started by sign_in and return a new Arclan API key. Pass the device_code from sign_in. If the user has not authorized in the browser yet, this returns status "pending" — wait poll_interval_seconds and call again. The api_key is shown ONCE; store it and send it as "Authorization: Bearer <key>".
{ "type": "object", "required": [ "device_code" ], "properties": { "device_code": { "type": "string", "description": "The device_code returned by sign_in" } } }arguments 12 lines
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's id567bc1157b7cdfbc.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/567bc1157b7cdfbc/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/567bc1157b7cdfbc?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.