Metadata-Version: 2.3
Name: mcp-pr-recommender
Version: 0.1.0
Summary: AI-powered MCP server for intelligent PR grouping recommendations
License: MIT
Keywords: mcp,model-context-protocol,ai,pull-requests,mcp-server,openai
Author: Manav Gupta
Author-email: manavg@gmail.com
Requires-Python: >=3.10,<4.0
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
Classifier: Topic :: Software Development :: Version Control
Requires-Dist: click (>=8.1.7,<9.0.0)
Requires-Dist: fastapi (>=0.116.1,<0.117.0)
Requires-Dist: fastmcp (>=2.6.1,<3.0.0)
Requires-Dist: openai (>=1.0.0,<2.0.0)
Requires-Dist: pathlib (>=1.0.1,<2.0.0)
Requires-Dist: pydantic-settings (>=2.10.1,<3.0.0)
Requires-Dist: pydantic[mypy] (>=2.11.7,<3.0.0)
Requires-Dist: sse-starlette (>=2.4.1,<3.0.0)
Requires-Dist: typing-extensions (>=4.8.0,<5.0.0)
Requires-Dist: uvicorn (>=0.35.0,<0.36.0)
Project-URL: Documentation, https://github.com/manavgup/mcp_pr_recommender#readme
Project-URL: Homepage, https://github.com/manavgup/mcp_pr_recommender
Project-URL: Repository, https://github.com/manavgup/mcp_pr_recommender
Description-Content-Type: text/markdown

# MCP PR Recommender

## Overview
The MCP PR Recommender is an intelligent PR boundary detection and recommendation system designed to analyze git changes and generate atomic, logically-grouped pull request (PR) recommendations. It aims to optimize code review efficiency and deployment safety by providing structured PR suggestions with titles, descriptions, and rationale.

## Features
- Generate PR recommendations from git analysis data.
- Analyze feasibility and risks of specific PR recommendations.
- Retrieve available PR grouping strategies and settings.
- Validate generated PR recommendations for quality, completeness, and atomicity.
- Supports both STDIO and HTTP transport protocols for flexible integration.

## Usage
The server can be run in different modes:
- **STDIO mode**: For direct MCP client connections.
- **HTTP mode**: For integration with MCP Gateway or other HTTP clients.

### Running the server
```bash
# Run in STDIO mode (default)
python -m mcp_pr_recommender.main --transport stdio

# Run in HTTP mode
python -m mcp_pr_recommender.main --transport streamable-http --host 127.0.0.1 --port 9071
```

## Input and Output
- **Input**: Expects git analysis data from the `mcp_local_repo_analyzer` project.
- **Output**: Structured PR recommendations including grouping, titles, descriptions, and rationale.

## Tools Provided
- `generate_pr_recommendations`: Generate PR recommendations from git analysis.
- `analyze_pr_feasibility`: Analyze feasibility and risks of PR recommendations.
- `get_strategy_options`: Get available grouping strategies.
- `validate_pr_recommendations`: Validate PR recommendations for quality.

## License
Apache-2.0 License

## Author
Manav Gupta &lt;manavg@gmail.com&gt;

