Verified record · from the answer index

@piagent/platform

Guardrails for AI coding agents: blocks secret reads, destructive commands, and unapproved MCP servers before the tool call runs. Ships project profiles, capability locks, a context engine, and task verification.

claude mcp add platform -- npx -y @piagent/platform

npm:@piagent/platform · published by vt-mmm · source repository