Skip to main content
Glama
parthamehta123

MCP Code Reviewer

๐Ÿค– MCP Code Reviewer Demo

CI Python License

This project demonstrates Model Context Protocol (MCP) with an AI-powered Code Reviewer.

Features

  • analyze_code: Finds basic issues in Python code

  • suggest_refactor: Suggests improvements (e.g., replace print with logging)

  • write_tests: Auto-generates placeholder unit tests

  • Agentic Mode: Automatically analyzes โ†’ refactors โ†’ re-analyzes code until clean

Quick Start

pip install -r requirements.txt
python -m mcp_code_reviewer.mcp_server   # start server
python -m mcp_code_reviewer.mcp_client   # run demo client

๐Ÿš€ Using Makefile

For convenience, a Makefile is provided:

make install       # install dependencies
make server        # run MCP server
make client        # run demo client
make client-agent  # run demo client in agentic loop mode
make test          # run tests
make clean         # remove caches and logs

๐Ÿ“Š Demo Output

Standard Demo (make client)

Available tools: ['analyze_code', 'suggest_refactor', 'write_tests']

๐Ÿ” Analysis:
{
  "issues": ["Consider using logging instead of print statements."],
  "line_count": 2
}

๐Ÿ›  Refactor Suggestion:
{
  "original": "def foo():\n    print('Hello')",
  "refactored": "def foo():\n    logger.info('Hello')"
}

๐Ÿงช Generated Tests:
{
  "tests": "def test_placeholder():\n    assert True"
}

๐Ÿค– Agentic Mode Demo (make client-agent)

๐Ÿ”„ Iteration 1: Analyzing code...
Analysis: {
  "issues": ["Consider using logging instead of print statements."],
  "line_count": 2
}
โš ๏ธ Issues found, applying refactor...

๐Ÿ”„ Iteration 2: Analyzing code...
Analysis: {
  "issues": [],
  "line_count": 2
}
โœ… No issues found! Code is clean.

Final Code:
def foo():
    logger.info('Hello')

Why This Project?

  • Showcases MCP server + client implementation

  • Demonstrates GenAI-style tooling (review, refactor, tests)

  • Adds Agentic AI loop to show self-improving code refinement

  • Strong example of MCP + GenAI + automation for recruiters

Next Steps

  • Integrate with real LLMs for deeper code analysis

  • Expand test coverage & CI integration

  • Record an asciinema demo and embed it here for a live showcase

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/parthamehta123/mcp-code-reviewer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server