# Code Analysis MCP Server A Model Context Protocol (MCP) server that enables AI models to understand and analyze codebases through natural language conversations. ## Highlights - **Natural Code Exploration**: Ask high-level questions about your codebase \`\`\` "What are all the different payment providers integrated in the system?" \`\`\` - **Deep Code Understanding**: Extract insights about data models and system architecture \`\`\` "How does the user authentication flow work from frontend to database?" \`\`\` - **Dynamic Analysis**: Trace data flows and understand system relationships \`\`\` "Show me all the places where we calculate transaction fees" \`\`\` ## Limitations This tool is a simpler alternative to more sophisticated code analysis tools / copilot like [Aider](https://aider.chat/). While it lacks the advanced code analysis capabilities and robustness of tools like Aider, it offers a lightweight solution for codebase exploration if you already have a Claude Pro subscription. The main advantages are: - **Cost-Effective**: Using your existing Claude Pro subscription means no additional API costs, unlike tools that can get expensive when analyzing large codebases - **Simple Setup**: Quick to get started with minimal configuration - **Basic Analysis**: Good for high-level code understanding and exploration Note that due to its simpler approach to code analysis, it may make more errors or provide less detailed insights compared to more specialized tools. ## Quick Start 1. Install the server: \`\`\`bash git clone https://github.com/saiprashanths/code-analysis-mcp.git cd code-analysis-mcp \`\`\` 2. Install [Claude Desktop App](https://claude.ai/download). For more instructions on setting up an MCP Server with Claude Desktop app, [see docs](https://modelcontextprotocol.io/quickstart/user) 3. Configure the server in Claude Desktop's configuration file: - macOS: \`~/Library/Application Support/Claude/claude_desktop_config.json\` - Windows: \`%APPDATA%\Claude\claude_desktop_config.json\` \`\`\`json \{ "mcpServers": \{ "code-analysis": \{ "command": "uv", "args": [ "--directory", "/PATH/TO/YOUR/REPO", "run", "code_analysis.py" ] \} \} \} \`\`\` 4. Restart Claude Desktop and start analyzing your code! 5. Ensure the tool is correctly setup - Clicking the tools icon should display the \`code-analysis\` tools - Clicking the integrations button should display the \`analyze_code_repository\` prompt ## Example Usage Here's how you might use the tool to understand a complex codebase: Start by clicking on the \`analyze_code_repository\` prompt shown below. That will guide you through the process to initialize the repo and get started. \`\`\`text You: How does the transaction processing work in this system? Claude: Let me analyze the data flow for transactions. Looking at the codebase, I can see that transaction processing happens through several key components: 1. Raw transaction data is captured in the \`TransactionEvent\` model with fields for: - Payment status - Amount - Fee calculations - Processing timestamps 2. This data is then processed through the PaymentSummary model, which: - Validates payment provider responses - Calculates processing fees - Records transaction status Would you like me to explain any part of this in more detail? You: What are the key database tables involved? Claude: The main tables in the transaction processing pipeline are: 1. transaction_events: Stores raw payment events 2. payment_summary: Processed transaction records 3. payment_providers: Provider configuration 4. merchant_accounts: Account-specific settings Let me know if you'd like to see the schema for any of these tables! \`\`\` ## Available Tools ### initialize_repository Initialize a code repository for analysis: \`\`\`python initialize_repository("/path/to/repo") # Output: Successfully initialized code repository at: /path/to/repo \`\`\` ### get_repo_info Retrieve information about the initialized repository: \`\`\`python get_repo_info() # Output: # Code Repository Information: # Path: /path/to/repo # Exists: True # Is Directory: True # Found .gitignore file \`\`\` ### get_repo_structure Examine repository file structure: \`\`\`python get_repo_structure(depth=2) # Output: # src/ # api/ # routes.py # models.py # utils/ # helpers.py # main.py \`\`\` ### read_file Read and analyze specific files: \`\`\`python read_file("src/api/models.py") # Output: # File: src/api/models.py # Language: python # Size: 2.3 KB # # [File contents...] \`\`\` ## Technical Details - Default scanning depth: 3 levels - Maximum file size: 1MB - Maximum lines per file: 1000 - Ignores paths listed in .gitignore - Local file system access only - Validates file paths to prevent directory traversal ## License This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.