Free security tool

Check your MCP server’s security

Is your MCP server safe to connect to Claude, ChatGPT and Cursor? Check its login, OAuth setup and open tools in about 10 seconds. Read-only and free.

Enter the exact endpoint your AI clients use, such as https://mcp.example.com/mcp. Only check servers you own or are allowed to test.

Free · No sign-up · No email needed. Only check servers you own or are allowed to test. We never call your tools or send login details.

What a well protected MCP server does

  • Answers 401 to anyone without a token, and points to its login in the WWW-Authenticate header.
  • Publishes OAuth discovery documents and supports PKCE with S256.
  • Uses HTTPS everywhere, with a valid certificate and HSTS.
  • Checks the Origin header, so web pages can’t reach a local or internal copy.
  • Marks tools that change data, so AI clients ask the user first.

The most common problems we see

  • An open server whose tools can write, delete or send messages.
  • Login works in one client but not others, because discovery documents are missing.
  • Tool descriptions that contain instructions for the AI instead of plain descriptions.
  • Debug servers left online after testing.

Frequently asked questions

What does the MCP security checker test?

It connects to your server the way an AI client does, with an MCP “initialize” request. It checks HTTPS and the certificate, whether a login is required, your OAuth discovery documents and PKCE support, CORS and HSTS headers, and version leaks. If the server is open, it lists the tools and flags risky ones without safety hints, prompt-injection phrases in tool descriptions, and whether requests from foreign websites are refused.

Is the check safe for my server?

Yes. It sends a handful of requests, never calls a tool, never sends passwords or tokens, and closes its session when done. Only check servers you own or are allowed to test.

My server needs a login. Can you still check it?

Yes, and that is the best case. We check that strangers get a 401 reply, that the reply tells AI clients where to log in, and that your login server supports PKCE with S256 over HTTPS, as the MCP specification asks. We don’t look at the tools behind the login.

Is an MCP server without login always unsafe?

No. A server that only shares public, read-only information can be open, like public documentation. It becomes risky when open tools can change data, send messages or reach private systems. The checker tells you which case you are in.

What is tool poisoning?

It is a prompt-injection attack hidden in a tool’s description, such as “ignore previous instructions” or a request to read secret files. AI clients read these descriptions, so hidden orders can change what the AI does. The checker looks for common phrases; a manual review finds more.

Does it replace a security review?

No. It checks the outside of your server in seconds. A full review also tests what each tool can reach, permission scopes, logging and real prompt-injection attempts.

MCP server development · MCP server security checklist · What is an MCP server? · All free tools