# MCP Trust Index

> Curated, trust-first index of vetted MCP servers — scored tiers, monthly re-verified. Read-only.

- name: fund.staas/mcp-trust-index
- version: 1.0.0
- connection class: unknown (unknown)
- trust: 92/100
- quality: 71/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/fund.staas%2Fmcp-trust-index
- tools: https://api.protogrid.dev/v1/servers/fund.staas%2Fmcp-trust-index/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mcp-trust-index": {
      "type": "http",
      "url": "https://staas.fund/mcp/server"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 85
- provenance: 85
- drivers: +repository +dns-namespace +website +reachable +uptime-97% ~updated-60d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 71/100 (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: 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: get_changelog (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_servers (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 396 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history not recorded yet

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

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

- tools: 5, about 396 tokens to load them all
- badge: [![protogrid quality](https://protogrid.dev/badge/fund.staas/mcp-trust-index.svg)](https://protogrid.dev/servers/fund.staas/mcp-trust-index)
- 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://staas.fund/mcp/server (streamable-http, auth unknown, reachable true, uptime30d 0.9745763)

## Packages

_none_

## Tools (5)

- `get_changelog`: Public log of every addition, removal, and re-score on the Trust Index, with reasoning.
- `get_rubric`: The full MCP Trust Index methodology as markdown: the 5 gates every server must pass, the 4 scoring dimensions, trust tiers, and editorial policies.
- `get_server`: Full Trust Index record for a single listed server: score, tier, publisher, description with caveats, category, install command, and links. Name is matched case-insensitively.
- `get_watchlist`: Servers the Index deliberately does not score: closed-source hosted vendor endpoints and platform-native MCP capabilities (no inspectable code to gate), plus open servers being watched that have not yet passed the gates.
- `search_servers`: Search the MCP Trust Index for vetted MCP servers. Filter by free-text query (matched against name, publisher, description, and category), category, and/or trust tier. Returns compact records sorted by score. Call with no arguments to list the entire index.