Gargeya-Grey/Documenter-MCP
If you are the rightful owner of Documenter-MCP and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
The MCP Documentation Server is designed to automate the analysis and checking of code documentation across various programming languages, ensuring quality and consistency without altering the source files.
MCP Documentation Server
This project implements an MCP (Model Coordination Protocol) server for automated code documentation analysis and checking. It focuses on identifying documentation issues in codebases across multiple programming languages without modifying source files.
Features
- Multi-language Support: Works with Python, JavaScript/TypeScript, Java, C++, Go, and more
- Documentation Checking: Verifies presence, format, and completeness of documentation
- Documentation Evaluation: Assesses clarity, consistency, and synchronization with code
- MCP Integration: Works as an MCP server for integration with other tools
Installation
pip install -r requirements.txt
Usage
Command Line Interface
# Analyze a project for documentation issues
python -m src.server analyze /path/to/project
# Check documentation without making changes
python -m src.server check /path/to/project
As an MCP Server
# Run as MCP server
python -m src.server --mcp
Configuration
The server can be configured using a YAML or TOML configuration file. See config.example.yaml
for an example configuration.
Project Structure
src/
āāā cli.py # Command-line interface
āāā server.py # Main MCP server implementation
āāā config.py # Configuration management
āāā logger.py # Logging setup
āāā models.py # Data models
āāā core/
ā āāā orchestrator.py # Core orchestration logic
āāā parsers/
ā āāā base.py # Base parser and Python parser
ā āāā __init__.py
āāā analyzers/
ā āāā checker.py # Documentation checking
ā āāā evaluator.py # Documentation evaluation
ā āāā __init__.py
āāā generators/
āāā __init__.py
Development
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Run tests
- Submit a pull request
License
MIT License - see LICENSE file for details.