10 skills (repositories by PrefectHQ) · sorted by popularity
Take a selected FastMCP bug from a reproducible failure to a focused fix. Check compatibility, run required validation, prepare a pull request, and follow automated checks and review feedback after publication.
Build, extend, or review Python FastMCP servers using documentation for the installed version. Design operations that agents can discover and use, then check input definitions, results, error handling, and representative agent workflows.
Write and revise FastMCP documentation pages with consistent structure, clear explanations, and runnable code examples. Covers accessibility, link and Python checks, and the publishing steps needed to confirm changes reach the live site.
Review a FastMCP pull request for justified behavior, implementation correctness, and compatibility. Independently check the proposed change, assess automated checks and reviewer feedback, and report a verdict tied to the exact revision examined.
Evaluate an incoming FastMCP issue and its linked pull requests. Check whether the reported behavior is a supported bug, assess the proposed contribution, and recommend assigning the contributor, declining, or seeking a specific maintainer decision.
Prepare and publish FastMCP releases, from reviewing changes and crediting contributors to updating changelogs, creating release tags, checking Python package publication on PyPI, and confirming that the documentation site reflects the release.
Write regression tests that catch recurring bugs in FastMCP changes using pytest. Covers reproducing failures before a fix, testing requests without a network server, and checking outgoing requests while replacing external services with test substitutes.
Discover MCP servers and inspect their available tools from the command line, then invoke operations with typed arguments or JSON. Use local files, remote endpoints, or configured server names, and return structured output for scripts.
Find worthwhile FastMCP issues within a backlog or release window. Investigate user impact, intended behavior, likely causes, and existing pull requests, then recommend concrete candidates with links and next steps.
Assess FastMCP vulnerability reports by preserving evidence, reproducing claims, and identifying which component owns the failed protection. Establish affected versions and realistic impact, review proposed fixes, and recommend how the report should be handled.