FastMCP tests

SkillDocs & knowledge

python-tests is a skill that helps an agent write regression tests for FastMCP changes. It uses pytest fixtures, in-memory clients, and protocol boundaries to check that a change behaves as expected. The person using an agent gets tests that exercise the server without a live network connection.

Use FastMCP tests in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add FastMCP tests and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the FastMCP tests skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have a Python project with FastMCP and pytest available.

FastMCP testsStart free

What your AI can do with it

  • Write regression tests for FastMCP changes with pytest
  • Use FastMCP pytest fixtures in test files
  • Drive an in-memory client against a FastMCP server
  • Test behavior at protocol boundaries
  • Turn a described FastMCP change into a failing then passing test

Getting started

  1. Have a Python project with FastMCP and pytest available.
  2. Add the skill to your agent so it can write test files for FastMCP changes.
  3. Point the agent at the FastMCP change that needs a regression test.
  4. Run the generated tests with pytest and check that they fail before the fix and pass after it.

What this skill tells your AI

The instructions your AI receives, as published by prefecthq/fastmcp in .agents/skills/python-tests/SKILL.md and read by ahel’s review.

Read nearby tests and the repository's validation requirements first. Extend the owning test module when it remains readable; use a focused module when the existing one is already too large.

For a bug fix, run the regression against unchanged code and confirm it fails for the reported reason, then run it with the fix. An import error or broken fixture is not a reproduced bug. Include supported adjacent behavior that the same branch could change, especially omitted defaults and explicit overrides.

  • Async tests need no marker: asyncio_mode = "auto" is configured globally.
  • Use Client(server) for real MCP dispatch without a network server. Use HTTP transport only when network behavior is the subject.
  • Mock external boundaries, not the FastMCP functions under test. For OpenAPI requests, capture the outgoing request with httpx2.MockTransport and assert its bytes, headers, or decoded parameters.
  • Keep imports at module scope. Prefer function-scoped fixtures and tmp_path for files.
  • Parameterize variations of one contract; separate unrelated behavior. For JSON, equality alone does not distinguish True from 1: check the resulting type when type preservation matters.
  • Use existing inline_snapshot conventions for complex schema assertions. Inspect generated snapshots rather than accepting them blindly.
  • The default timeout is five seconds. Use the repository's integration conventions for tests that legitimately need more time.

Run focused tests during development, then the full commands required by AGENTS.md before committing. If a failure appears unrelated, reproduce it on the unchanged base; do not call it pre-existing from the test name alone.

Signals

GitHub stars
28k
Forks
2k
Last commit
Oct 2026

Questions

Does this skill write regression tests for FastMCP changes?
Yes. It writes regression tests for FastMCP changes using pytest fixtures, in-memory clients, and protocol boundaries.
Does it use pytest fixtures and in-memory clients?
Yes. The tests it writes use FastMCP pytest fixtures and in-memory clients, so they do not need a live network connection.
Can it test behavior at protocol boundaries?
Yes. Protocol boundaries are one of the things the skill uses when writing regression tests for FastMCP changes.
Do I need a running FastMCP server to run the tests?
No. The tests use in-memory clients, so they exercise the server without a live network connection.
What do I need installed before using this skill?
You need a Python project with FastMCP and pytest available, and the skill added to your agent.
Advanced
Item type
skill
Key
python-tests
Source
github.com/prefecthq/fastmcp