# mcpindex

> The MCP server index that vets servers, not just lists them. Advisory screen before you install.

- name: io.github.gautamgb/mcp-server-mcpindex
- version: 0.4.0
- connection class: R0 (autonomous)
- trust: 90/100
- quality: 86/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.gautamgb%2Fmcp-server-mcpindex
- tools: https://api.protogrid.dev/v1/servers/io.github.gautamgb%2Fmcp-server-mcpindex/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "mcp-server-mcpindex": {
      "type": "http",
      "url": "https://mcpindex.ai/api/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 75
- drivers: +repository +website +reachable +uptime-100% ~updated-64d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 86/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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_install_command (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_tool_trust (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); assess_server (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 782 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: 100 (weight 15)

- pass `deps.known_vulns`: no known advisory in 4 resolved packages
- pass `deps.mcp_sdk_version`: @modelcontextprotocol/server 2.1.0, no known advisory
- pass `deps.resolvable`: mcp-server-mcpindex@0.4.0 resolved: 4 packages

- tools: 6, about 782 tokens to load them all
- tool set hash: b91455e2fc4c58ac5e90626622f57fb4
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.gautamgb/mcp-server-mcpindex.svg)](https://protogrid.dev/servers/io.github.gautamgb/mcp-server-mcpindex)
- 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 mcp-server-mcpindex@0.4.0: resolved, 3 dependencies, MCP SDK @modelcontextprotocol/server 2.1.0

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://mcpindex.ai/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

- npm mcp-server-mcpindex@0.4.0

## Tools (6)

- `assess_server`: Aggregated pre-flight trust assessment across all tools on an MCP server. Same verdict shape as check_tool_trust. Use for "is THIS server worth integrating?" decisions. v1 advisory; conformance monitored not enforced; verdicts may be UNVERIFIED if not yet probed.
- `check_tool_trust`: Pre-invocation advisory screen for a specific tool on an MCP server. Returns an advisory verdict object (directive ALLOW | DENY | REVIEW | UNVERIFIED, dimensions, freshness). At v1 the public screen produces REVIEW or UNVERIFIED only - ALLOW/DENY are reserved. Not the in-path gate (mcpindex-gate). Agents SHOULD treat UNVERIFIED as "human review required", never as ALLOW.
- `compare_servers`: Side-by-side comparison of 2-5 MCP servers - quality scores, install paths, env vars.
- `get_install_command`: Get the exact install command for a given MCP server and client. Returns a JSON block ready to paste into the client config.
- `recommend_mcp_for_task`: Recommend the best MCP servers for a natural-language task. Returns top 3 ranked picks with reasoning, install commands, and quality scores. Use this when the user asks for the right MCP server for a task they want to do.
- `search_mcp_servers`: Keyword + semantic search across every MCP server mcpindex indexes. Use when the user knows what tool category they want but not which server.