<!-- mcp-name: io.github.saagpatel/mcp-trust --> > Check before you connect. A neutral, public danger grade for the MCP servers > your AI agents rely on. **Live:** [mcp-trust.vercel.app](https://mcp-trust.vercel.app) > **Not yet published to PyPI.** Install from source using the Quickstart below. `mcp-trust` runs as a read-only MCP server so an agent can check a server's