Skip to content
mcp/harbor
Verified official

openclaw output vetter mcp MCP

v1.3.0

io.github.temurkhan13/openclaw-output-vetter-mcp

Verify AI agent claims vs reality: inline grounding-check + swallowed-exception + transcript review.

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add openclaw-output-vetter-mcp -- uvx openclaw-output-vetter-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.