Yoshi
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 decisions with per-server configuration, allowlisting, and logging. Zero dependencies, ~60ms latency.
Works with: Claude Code, Cursor, Claude Desktop, Codex CLI, Gemini CLI, Cline, Windsurf, VS Code
Category: Productivity — see all ranked ›
- tashan score: 36.0
- Adoption: 1 repos
- Health: active
- GitHub stars: 1
- Contributors: 1
- License: MIT
Security audit
Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.
source ↗ · plugin:aliksir/mcp-yoshi/mcp-yoshi
Already running this? npx tashan-cli doctor checks your whole config against the Index — how it works ›