MCP Evals

Can an AI agent actually use your MCP server?

A connection test proves your server speaks the protocol. An eval shows whether a model can work out which tool to call and come back with the right answer.

Any reachable MCP server · Read-only tools by default · No server? Use a public mock

How it works

  1. 1

    Detect your tools

    Connect any MCP server you can reach. The tool list is read, and real values are pulled from read-only tools.

  2. 2

    Write real tasks

    Questions a user would actually ask, like “what is the total for order 1041?”, grounded in your data.

  3. 3

    Let an agent drive

    A live model gets only your tool names and descriptions, and has to finish each task on its own.

  4. 4

    Get a graded report

    Every task passes or fails, with the full trace of tool calls behind it. Re-run it after each change.

What it catches that a tester can’t

Right calls, wrong answer

Every call succeeded and every argument validated, and the answer was still wrong. No schema check can see this.

The wrong tool

Two tools sound alike, and the agent reaches for the one your description made look right.

Wasted calls

A description leaves out that a search also matches email, so the agent burns five calls to find one customer.

See a finished run

Step through a real run, screen by screen, exactly as the product shows it.

DemoA finished run on a made-up orders server, replayed. Nothing connects to a real server, no model is called, and nothing is charged.

Run your MCP server against real AI models — a full, end-to-end test, not a mock.

It detects your tools, writes the tasks a real user would ask, then turns a live model loose to complete each one using your server — just like a real client. You watch the whole agentic run: every tool call, where it gets stuck, and whether it lands the right answer. So you learn if AI can actually use your server — and which of 60+ models do it best.

Run this against your own server

Paste a URL. Tools are detected, tasks are written from your real data, and an agent runs them. Writing tools stay out unless you opt in.

Run evals →

Questions people ask

What is an MCP eval?

A task a model has to complete using only your server’s tools. It checks whether an agent can pick the right tool from your descriptions and reach a correct answer, not whether the endpoint returns 200.

Are the results deterministic?

No. Models write, drive and grade the evals, so the same suite can come out differently next time. We only see what your server exposes, never your database or what the right answer should have been. Treat a run as evidence, not proof.

Will it change data on my server?

Not by default. Tools that write are left out of the suite unless you opt in.

How is this different from an MCP client or inspector?

A client tells you the protocol works. An eval tells you the server is usable. Try the inspector if the protocol is what you want to check.

MCP Evals — Test Whether an AI Agent Can Actually Use Your MCP Server | MCP Playground