Free tool

MCP Server Tester

Check that your MCP server actually works. Paste the URL and get a pass/fail report on the connection, the handshake, the transport and the tools it advertises.

Works with streamable HTTP and SSE endpoints, for example https://mcp.example.com/mcp
This server needs authentication
Used for this one request and never stored.

It passes. Now let someone else try it.

A green checklist proves your server works. It does not show a customer what it does. Point MCP Showcase at the same URL and get a live playground they can try in a browser.

How it works

link
Paste your server URL

A deployed endpoint, not a local process. Add a bearer token if the server needs one — it is used once and never stored.

play_circle
We run the real client

A genuine MCP handshake, streamable HTTP first and SSE as a fallback — exactly what Claude, Cursor or VS Code will do.

checklist
See what passed and what failed

A check-by-check report plus the raw request and response log, so a failure points at the step that broke rather than at a generic error.

Test an MCP server without installing anything

Paste a Model Context Protocol endpoint above and this MCP server tester runs a real client against it — the same sequence Claude Desktop, Cursor or VS Code run when they connect. It opens the connection, performs the initialize handshake, negotiates a protocol version and calls tools/list, then reports each step separately as a pass or a failure.

That separation is the point. A client that cannot see your server gives you one unhelpful error; this gives you seven answers, so you find out whether the endpoint is unreachable, the handshake is failing, the transport is mismatched or the tool list is simply empty.

What gets checked

  • Endpoint reachable — the URL accepts a connection and answers.
  • MCP handshakeinitialize completes and a protocol version is negotiated. A server that accepts TCP but fails here is running, but is not speaking MCP.
  • Transport — whether it answered on streamable HTTP or on the older SSE transport, which is the single most common cause of "my client cannot see it".
  • Server identity — the name and version reported in the handshake.
  • Tools advertised — how many tools the server lists, and their names.
  • Resources and prompts — both optional in the spec, so absence is reported rather than treated as a fault.

When your server works locally but not here

This is the most common reason people reach for a hosted tester, and it is almost always one of three things. The endpoint is not publicly reachable — it is bound to localhost, or behind a firewall, or the deploy has not finished. The deployed path differs from the local one: MCP servers are variously mounted at /mcp, /sse or the root, and the path that worked with mcp dev is not always the one your host exposes. Or the deployed build is simply older than the one on your machine.

The request and response log under the result distinguishes all three. A connection refused looks nothing like a 404, and a 401 tells you the server is fine and wants a token.

What this does not test

No tool is ever called. This checks the layer underneath — connection, handshake, advertisement — which has to work before an agent can call anything at all. It will not tell you whether a tool validates its input or returns the right answer. If you want to see the tool schemas themselves, use the MCP Inspector; if you want to know whether the server is safe to point an agent at, run the security scanner.

Related guides

Passing the test is not the same as being usable

A green checklist tells you the plumbing works. It tells a prospective customer nothing at all — they cannot read a handshake, and a list of tool names is not a demonstration. That is what MCP Showcase is for: point it at the same URL and it produces a shareable playground page where anyone can try the tools in a browser, with generated documentation for each one and copy-paste setup for their own client.

Frequently asked questions

Connect a real MCP client to it and confirm three things: that the endpoint answers, that the initialize handshake completes and negotiates a protocol version, and that it lists the tools you expect. This tester does all three against a deployed URL and reports each one separately.

Almost always one of three things: the endpoint is not publicly reachable, the deployed path differs from the local one (/mcp versus /sse versus /), or the deployed build is older than the one on your machine. The request log below the result shows which.

No. It never calls a tool. It verifies that the server connects, completes the handshake and advertises its tools correctly — the layer that has to work before an agent can call anything at all.

They run the same handshake and differ in what they show you. The tester answers "does this work", as a pass/fail checklist. The Inspector answers "what is in here", listing every tool with its full JSON schema.

MCP is served over streamable HTTP or the older HTTP+SSE transport. A server that only speaks SSE still works with many clients, but newer ones increasingly try streamable HTTP first and some no longer fall back — which shows up as a client that simply cannot see your server.

More free MCP tools