Python
by Dave-Londoncommunityv0.8.0
116
10
An MCP server that exposes structured Python tooling for package installation, linting, type checking, testing, formatting, and vulnerability auditing. It wraps common Python CLI tools and returns token-efficient JSON output for AI agents.
From the registry: Structured Python tool output (ruff, mypy, pip-audit, pip-install) as typed JSON.
Install & configure
Prerequisites
- required
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `python` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Node.js is required to run the MCP server via npx. (https://nodejs.org/'}],)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@paretools/python"]
Note: README provides a direct npx-based stdio configuration. No environment variables are documented.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: README provides a direct npx-based stdio configuration. No environment variables are documented.
Tools (8)
pip-install
Install packages and return a summary of installed items
mypy
Return type-check diagnostics including file, line, severity, and message
ruff-check
Return lint diagnostics including file, line, code, and message
pip-audit
Return a vulnerability report for installed packages
pytest
Run tests and return structured pass/fail results
uv-install
Install packages via uv with a structured summary
uv-run
Run a command in a uv-managed environment
black
Format code with Black and return changed/unchanged files
Packages
@paretools/python
npmv0.8.0transport: stdio
Details
- Language
- TypeScript
- License
- MIT
- Released
- Feb 14, 2026
- Last commit
- Apr 8, 2026
- Registry name
- io.github.Dave-London/python