Code Reviewer Fixer Agent

What is Code Reviewer Fixer Agent?

This AI agent analyzes code repositories, detects potential security vulnerabilities, reviews code quality, and suggests fixes based on Sentry error logs. It integrates with GitHub and Sentry MCP servers, and is part of the "A New AI Agent Every Day!" series.

How to use Code Reviewer Fixer Agent?

Install prerequisites (Python 3.9+, Git, virtual environment, Node.js for MCP), clone the repository, install dependencies with pip install -r requirements.txt, and create a .env file with Azure OpenAI, GitHub, and Sentry tokens. Start the FastAPI server with uvicorn upsonicai:app --reload and open the UI at http://127.0.0.1:8000/. Configure MCP servers by adding GitHub and Sentry entries to your MCP configuration file.

Key features of Code Reviewer Fixer Agent

• Fetches recent commits from GitHub/GitLab repositories
• Analyzes code quality and detects security vulnerabilities
• Retrieves error logs from Sentry
• Provides actionable insights and fixes for detected issues
• Integrates with GitHub and Sentry MCP servers

Use cases of Code Reviewer Fixer Agent

• Automated code review after each commit
• Detect security vulnerabilities in code repositories
• Fix issues identified from Sentry error logs
• Continuous code quality monitoring and improvement

FAQ from Code Reviewer Fixer Agent

What are the prerequisites to run the agent?

Python 3.9 or higher, Git, a virtual environment (recommended), and Node.js for MCP.

What environment variables need to be configured?

You need to set AZURE_OPENAI_ENDPOINT, AZURE_OPENAI_API_VERSION, AZURE_OPENAI_API_KEY, GITHUB_PERSONAL_ACCESS_TOKEN, and SENTRY_AUTH_TOKEN in a .env file.

How do I start the application?

Run uvicorn upsonicai:app --reload in the project root, then open http://127.0.0.1:8000/ in your browser.

How do I configure the MCP servers?

Modify your MCP configuration to include a github server using npx and a sentry server using python -m mcp_server_sentry, each with the appropriate token.