docvet 1.8: MCP Server — AI Agents Can Run docvet Directly

[Alberto-Codes]

docvet ships a Model Context Protocol server, so AI agents can run docstring quality checks and browse the rule catalog without leaving the conversation.

MCP tools

• docvet_check — run all checks on a directory or file, with full finding output in structured JSON
• docvet_rules — browse the rule catalog with summaries, fix guidance, and configuration info

Each rule in the catalog includes a guidance field explaining why the rule matters and how to fix violations, plus a fix_example with concrete before/after code. Agents can suggest specific fixes, not just report rule names.

How to use

# Start the MCP server
docvet mcp

# Or install as a pip extra
pip install docvet[mcp]

The server runs over stdio and works with any MCP-compatible client. Add it to your agent's MCP configuration and docvet becomes a tool the agent can call autonomously.

Docs · MCP Registry listing · PyPI