A command-line tool and MCP server that audits websites for AI-agent readiness and safety. It checks for hidden prompt injection, machine-readable signals like llms.txt, robots.txt, structured data, sitemap, and accountability links, then returns a score and findings.
From the registry: Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
Please install the `agent-readiness-auditor` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js 18 or newer** — Node.js version 18 or later is required to run the MCP server via npx. (https://nodejs.org/iguration uses the npm package via npx. No environment variables are documented or required.)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","agent-readiness-auditor","mcp"]
Note: The README documents Claude Code and Claude Desktop examples, both of which resolve to the same canonical stdio command: `npx -y agent-readiness-auditor mcp`. The server exposes one tool, `audit_site`, which takes a URL and returns audit results.
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.Meta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.