TrustFetch MCP
v1.0.0io.github.vohlsyr/trustfetch
Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
transport:streamable-http
Target client
run in your project directory
claude mcp add --transport http trustfetch https://trustfetch.duckdns.org/mcp/
Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs
This listing does not declare its tools. Connect the server and your client will discover them on the handshake.