pyfmcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pyfmcp Check my project with pytest and Ruff"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
PyFMCP
An easy-to-use, configurable, Python-focused Model Context Protocol providing tools for type-checking, testing and linting your code.
Requirements
Python 3.12+
An MCP-compatible client
uv(recommended) or another Python package installer
Related MCP server: mcp-server-analyzer
Usage
Run it from the project you want to inspect:
uv run pyfmcpDevelopment
uv sync --all-groups
uv run pytest
uv run ruff check .
uv run basedpyrightBuild the documentation with uv run mkdocs serve.
Contributions are welcome. Please open an issue or pull request with a focused change, tests where appropriate, and documentation for user-visible behavior.
License
Available Tools
3 toolsbasedpyrightC
Run basedpyright diagnostics
Inputs: paths. Returns: errors, warnings, exit_code, diagnostics
pytestC
Run pytest and return its JUnit XML report.
Inputs: paths. Returns: suites, exit_code
ruff_lintC
Run Ruff diagnostics
Inputs: paths. Returns: exit_code, diagnostics
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool targets a distinct aspect of Python development: type checking (basedpyright), testing (pytest), and linting (ruff_lint). There is no functional overlap between them, making selection unambiguous.
Two tools use the bare command name (basedpyright, pytest) while ruff_lint appends a descriptor. This is a minor deviation, but the naming is still predictable since each tool is recognizable by its underlying tool name.
Three tools is well-scoped for a Python development server covering static analysis, linting, and testing. Each tool has a clear purpose and the count is appropriate for the domain.
The set covers the core development loop of type checking, linting, and testing. A formatter or build tool could be added, but the current coverage is typical and workable for most Python projects.
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
One MCP server for all your MCP servers: code mode, per-tool permissions, approvals and audit.
MCP server for generating rough-draft project plans from natural-language prompts.
Related MCP Servers
- AlicenseAqualityDmaintenanceAn MCP server that exposes Pyright language server functionality for Python, providing tools for type checking, code completions, and finding definitions. It enables AI models to perform static analysis and code formatting through the Model Context Protocol.729 PyPIMIT
- AlicenseBqualityBmaintenanceAn MCP server that performs comprehensive Python code analysis using Ruff, ty, and Vulture for linting, type checking, and dead code detection.8144 PyPI11MIT
- AlicenseBqualityDmaintenanceAn MCP server that integrates Ruff linting, formatting, and code analysis tools with advanced logging and configuration options for AI coding assistants.41MIT
- AlicenseNot gradedqualityBmaintenanceThis MCP server enables automated maintenance and code analysis for Python/pytest repositories in isolated Docker environments. It supports read-only investigations, fix-and-verify tasks, and provides full audit trails with SQLite event history and artifact exports.MIT