mcp-yoshi

PackSecurity

Scans data going to and from your agent's connected tools and blocks threats like injected commands or leaked keys.

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

Real-time security filter for MCP tool communications. Works as a Claude Code hook to inspect all data sent to and received from MCP servers. Detects prompt injection, API key leakage, tool poisoning, ASCII smuggling, SSRF, Base64-encoded payloads, and Rug Pull attacks. Provides PASS/WARN/BLOCK deci

Signals

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

Advanced

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

github.com/anthropics/claude-plugins-community