This MCP server provides security guardrails for AI agents, including input validation, prompt injection detection, PII redaction, output filtering, policy enforcement, rate limiting, and audit logging.
From the registry: AI Agent Guardrails MCP server - security layer
$ git clone https://github.com/ExpertVagabond/guardrails-mcp-server.git && cd guardrails-mcp-server && npm installPlease install the `guardrails` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone and install** — Clone the repo and install dependencies Run: `git clone https://github.com/ExpertVagabond/guardrails-mcp-server.git && cd guardrails-mcp-server && npm install`
Canonical MCP server config (stdio transport):
- command: `node`
- args: ["/path/to/guardrails-mcp-server/index.js"]
Note: No npm package; install from source.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Dead code, security, secrets detection and code quality for Python, TypeScript, Go.