agent output guard for Claude Code

io.github.agenson-horrowitz/agent-output-guard

Validate and verify data from other agents before acting on it. Zero LLM costs.

client:Claude Code transport:stdio runtime:npm

Install agent output guard in Claude Code

run in your project directory

claude mcp add agent-output-guard -- npx -y @agenson-horrowitz/agent-output-guard-mcp

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs