# io.scorecard/mcp

> MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

- name: io.scorecard/mcp
- version: 2.1.1
- connection class: R2 (oauth_consent_once)
- trust: 78/100
- quality: 58/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.scorecard%2Fmcp
- tools: https://api.protogrid.dev/v1/servers/io.scorecard%2Fmcp/tools

**An agent can connect after a one-time OAuth consent by a human.** Remote endpoint behind OAuth 2. Tokens stay with the agent; the registry only exposes the authorization metadata.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "scorecard": {
      "type": "http",
      "url": "https://mcp.scorecard.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 25
- provenance: 75
- drivers: +repository +dns-namespace +reachable +uptime-100% -stale-403d
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 58/100 (needs work)

### protocol: n/a (weight 25)

- n/a `protocol.modern`, `protocol.stateless`, `protocol.transport`, `protocol.list_ttl`: no remote answered a protocol handshake (not probed yet, unreachable, or local-only)

### authorization: 83 (weight 15)

- pass `auth.prm`: Protected Resource Metadata (RFC 9728) published
- pass `auth.as_metadata`: authorization server metadata reachable
- warn `auth.cimd`: only Dynamic Client Registration, deprecated in 2026-07-28 in favour of CIMD
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: n/a (weight 30)

- n/a `tools.descriptions`, `tools.description_length`, `tools.schemas`, `tools.annotations`, `tools.directory_hints`, `tools.token_cost`, `tools.api_dump`: tool list unknown (behind auth, not probed, or empty)

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

- n/a `stability.changes`, `stability.rug_pull`: tool list unknown

### dependencies: 33 (weight 15)

- warn `deps.known_vulns`: 1 advisory of lower severity or without a published fix: GHSA-8988-4f7v-96qf in @opentelemetry/core@2.2.0 (indirect, fixed in 2.8.0)
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
- warn `deps.resolvable`: the dependency graph of scorecard-ai-mcp@2.1.1 resolved with errors, so advisories may be missing

- tools: unknown
- badge: [![protogrid quality](https://protogrid.dev/badge/io.scorecard/mcp.svg)](https://protogrid.dev/servers/io.scorecard/mcp)
- 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._

## Dependencies

- npm scorecard-ai-mcp@2.1.1: incomplete, 153 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h
  - GHSA-8988-4f7v-96qf (moderate) in `` @opentelemetry/core@2.2.0 ``, indirect, fixed in `` 2.8.0 ``, advisory summary: "OpenTelemetry Core: Unbounded memory allocation in W3C Baggage propagation" https://osv.dev/vulnerability/GHSA-8988-4f7v-96qf

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.scorecard.io/mcp (streamable-http, auth oauth2, reachable true, uptime30d 1)

## Packages

- npm scorecard-ai-mcp@2.1.1 secrets: SCORECARD_API_KEY

## Tools (0)

_none observed_