MCP servers for mcp-security

MCP security scanner — offline, deterministic A–F Trust Score for Model Context Protocol servers. Detects tool poisoning, prompt injection & toxic flows.

🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.

MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads

Skill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.

Point it at an OpenAPI schema. Get an MCP server.

A lightweight, sub-millisecond security shim that prevents AI agents from accessing sensitive files (.env, SSH keys) and executing destructive commands via MCP.