# MCP Vetted

> An AI-run search engine and installer for MCP servers. Every version is checked automatically and given a trust tier. Built for agents; people are welcome.

Every MCP server is found automatically, checked on each release (qualification, static scan, LLM claims check) and given a trust tier: indexed < scanned < verified < proven. Money never changes a tier or a rank.

## Connect

- MCP server (Streamable HTTP, no sign-in): https://mcpvetted.com/api/mcp
- REST API: https://mcpvetted.com/api/v1 (OpenAPI: https://mcpvetted.com/openapi.json)
- MCP Registry-compatible API (Scanned and up only): https://mcpvetted.com/api/registry/v0.1/servers
- Trust page per tool: https://mcpvetted.com/t/<slug> (Markdown: https://mcpvetted.com/t/<slug>.md)

## MCP tools

- search_tools: Searches the vetted index of MCP servers by keyword or by the job a tool does. Returns each result's trust tier, observed access, check results and trust page URL.
- get_tool: Returns one indexed tool by slug, registry name or server URL: versions, tier history, observed access and supported apps.
- get_trust_report: Returns each check's verdict and findings for one version of a tool, with the rules version and when each check ran.
- compare_tools: Compares 2 to 5 tools side by side on tier, observed access, agent-reported outcomes and latest release.
- get_install_config: Returns the exact install link, command or config block one app accepts for a tool, pinned to the vetted version, plus the access to show the user before installing. Records an install id for outcome reports.
- check_policy: Checks one tool against a minimum tier and a list of blocked access types, and returns allow or deny with the reasons.
- list_revocations: Lists tool versions revoked after failing a check, newest first, optionally since a date or for specific tools.
- submit_url (write): Adds a tool to the index from an address: a remote MCP server URL, a domain, a GitHub repo, or an npm or PyPI package. Reads the server's self-description without calling its tools, then runs the standard checks.
- report_outcome (write): Records whether a tool did its job after an install made with get_install_config. Reports from distinct agents feed the Proven tier.

## Docs

- [Agent quickstart](https://mcpvetted.com/docs)
- [API reference](https://mcpvetted.com/docs/api)
- [How we check](https://mcpvetted.com/methodology)
- [Revocations](https://mcpvetted.com/revocations)
- [Terms](https://mcpvetted.com/terms) · [Privacy](https://mcpvetted.com/privacy) · [Acceptable use](https://mcpvetted.com/acceptable-use)