Skip to content
mcp/harbor
Verified official

Infraveil Agent Guard MCP

v0.1.1

io.github.infraveilhq/agent-guard

Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.

transport:stdio runtime:pypi
View source Website

Target client

run in your project directory

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

claude mcp add agent-guard -e INFRAVEIL_GUARD_THRESHOLD=<INFRAVEIL_GUARD_THRESHOLD> -e INFRAVEIL_GUARD_MODE=<INFRAVEIL_GUARD_MODE> -e INFRAVEIL_GUARD_HOME=<INFRAVEIL_GUARD_HOME> -- uvx infraveil-guard

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.