# Arclan MCP Registry

> MCP registry: 138k servers crawled, handshake-validated, reliability-scored. 744 production-safe.

- name: ai.arclan/registry
- version: 0.2.0
- connection class: unknown (unknown)
- trust: 55/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.arclan%2Fregistry
- tools: https://api.protogrid.dev/v1/servers/ai.arclan%2Fregistry/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "arclan": {
      "type": "http",
      "url": "https://arclan.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 29
- freshness: 85
- provenance: 45
- drivers: +dns-namespace -unreachable(1 failures) ~updated-38d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2024-11-05; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: recommend_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); report_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 1,239 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,239 tokens to load them all
- tool set hash: 9c0587df379a6c49d61462cca86e7768
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.arclan/registry.svg)](https://protogrid.dev/servers/ai.arclan/registry)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://arclan.ai/mcp (streamable-http, auth none, reachable false, uptime30d 0.96581197)

## Packages

_none_

## Tools (4)

- `get_server`: 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.
- `query_registry`: 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.
- `recommend_server`: 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.
- `report_server`: 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).