protect-mcp

PackSecurity

Adds safety rules around an agent's connected tools, logging calls by default or requiring approvals before they run.

Unavailable. Delivery for this kind is on the roadmap — not serving yet.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

About this app

MCP security gateway that wraps any MCP server with per-tool policies, Ed25519-signed decision receipts, and human approval gates. Shadow mode (default) logs every tool call without blocking. Enforce mode applies per-tool allow/deny/rate-limit/approval policies. Every decision is cryptographically s

Signals

GitHub stars: 4k
Forks: 312
Last commit: Aug 2026

Advanced

Item type: plugin
Key: anthropics-claude-plugins-community-protect-mcp
Source: github.com/anthropics/claude-plugins-community

github.com/anthropics/claude-plugins-community