MCP Code Reviewer
Enables AI-powered code review and improvement, including analysis, refactoring suggestions, and automatic test generation, with an optional agentic loop for iterative refinement.
README
๐ค MCP Code Reviewer Demo
This project demonstrates Model Context Protocol (MCP) with an AI-powered Code Reviewer.
Features
analyze_code: Finds basic issues in Python codesuggest_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
๐ 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
๐ Demo Output
Standard Demo (make client)
Available tools: ['analyze_code', 'suggest_refactor', 'write_tests']
๐ Analysis:
{
"issues": ["Consider using logging instead of print statements."],
"line_count": 2
}
๐ Refactor Suggestion:
{
"original": "def foo():\n print('Hello')",
"refactored": "def foo():\n logger.info('Hello')"
}
๐งช Generated Tests:
{
"tests": "def test_placeholder():\n assert True"
}
๐ค Agentic Mode Demo (make client-agent)
๐ Iteration 1: Analyzing code...
Analysis: {
"issues": ["Consider using logging instead of print statements."],
"line_count": 2
}
โ ๏ธ Issues found, applying refactor...
๐ Iteration 2: Analyzing code...
Analysis: {
"issues": [],
"line_count": 2
}
โ
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.