Skip to content

CLAUDE.md

Latest commit

 

History

History
63 lines (42 loc) · 2.16 KB

CLAUDE.md

File metadata and controls

63 lines (42 loc) · 2.16 KB

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

This is a Model Context Protocol (MCP) server that provides seamless interaction with CodeGPT's Code Graphs. The server enables semantic code search, dependency analysis, and code retrieval across repository knowledge graphs.

Development Commands

# Build the project
npm run build

# Build and watch for changes during development
npm run watch

# Test the MCP server locally
node dist/index.js

# Debug MCP server with wrapper
node debug-mcp.js

Architecture

Core Components

  • src/index.ts: Main MCP server implementation with all tool definitions
  • debug-mcp.js: Wrapper script for debugging ES module compatibility
  • dist/: Compiled JavaScript output (generated by TypeScript)

MCP Tools Implemented

The server implements 6 main tools for interacting with CodeGPT's knowledge graphs:

  1. list-graphs: Lists available repository graphs (only when CODEGPT_GRAPH_ID not set)
  2. get-code: Retrieves complete code implementation of functionalities
  3. find-direct-connections: Explores immediate relationships in the code graph
  4. nodes-semantic-search: Semantic search for code functionalities
  5. docs-semantic-search: Semantic search through documentation
  6. get-usage-dependency-links: Deep dependency analysis for impact assessment

Configuration

The server uses environment variables for configuration:

  • CODEGPT_API_KEY (required): API key for CodeGPT service
  • CODEGPT_ORG_ID (optional): Organization ID
  • CODEGPT_GRAPH_ID (optional): Specific graph ID

Arguments can also be passed via command line in order: API_KEY, ORG_ID, GRAPH_ID.

Key Implementation Details

  • Uses @modelcontextprotocol/sdk for MCP protocol implementation
  • Implements dynamic schema generation based on environment variables
  • Includes extensive error handling and logging
  • TypeScript with ES2022 target and NodeNext modules
  • Communicates with CodeGPT API at https://api-mcp.codegpt.co/api/v1

Publishing

The package is published to npm as mcp-code-graph with binary entry point at dist/index.js.