MCP Server for AI Assistants

What is MCP?

The Model Context Protocol (MCP) is an open standard that lets AI assistants call outside tools. Connect an assistant to an MCP server and it can use that server's tools on its own while it answers you.

The tools, in your assistant

Every tool on the site that runs on our server is now also available over MCP:

https://rapidtoolset.com/api/mcp

That includes domain lookups (WHOIS, RDAP, DNS, SPF/DKIM/DMARC, subdomains, age, expiry and availability), IP lookups, website checks (TLS certificates, redirects, robots.txt, Open Graph, hreflang, JSON-LD, RSS feeds), blocklist checks and MAC address lookups.

Ask your assistant a question and it picks the right tool:

The MCP tools page lists them all, with each tool's description and input schema. Every tool runs the same code as its page on the site and only reads data, never changes anything.

How to connect

1. Create an API token on the Tokens page of your profile. It's shown only once, so copy it right away
2. Add the server to your AI client with the token in the Authorization header:

{
  "mcpServers": {
    "rapidtoolset": {
      "type": "http",
      "url": "https://rapidtoolset.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <token>"
      }
    }
  }
}

The server uses the Streamable HTTP transport. There's no OAuth sign-in, so the client needs to support custom headers.

Limits

Each account has a daily limits. Your profile dashboard shows how much of it is used and when it resets, and the Logs page lists your calls.

In testing

The MCP server is in testing, so for now it's open only to selected accounts. Other accounts get a message saying so when their client connects.