What is Mcp Code Graph

mcp-code-graph is an MCP Server designed for code graph analysis and visualization, enabling users to interact with knowledge graphs through CodeGPT.

Use cases

Use cases include analyzing code dependencies in large projects, visualizing code architecture, retrieving specific code implementations for debugging, and enhancing learning through interactive code exploration.

How to use

To use mcp-code-graph, you can access various tools such as ‘list_graphs’ to discover available repository graphs, ‘get_code’ to retrieve complete code implementations, and ‘find_direct_connections’ to explore immediate relationships within the code graph.

Key features

Key features include advanced graph-based queries, seamless interaction with multiple MCP Hosts (like ChatGPT and GitHub Copilot), and tools for listing graphs, retrieving code, and exploring code dependencies.

Where to use

mcp-code-graph can be used in software development, code analysis, and educational contexts where understanding code structure and relationships is crucial.

Deep Graph MCP Server by CodeGPT

A Model Context Protocol server that enables seamless interaction with Code Graphs.

How this works

This MCP allows you to interact with the knowledge graphs available in your CodeGPT account.

You’ll be able to use these advanced graph-based queries across different MCP Hosts such as ChatGPT, Cursor, Windsurf, CodeGPT Extension, GitHub Copilot, Claude Desktop, and others.

Available Tools

list_graphs: Lists available repository graphs with basic information.

get_code: Retrieves the complete source code for a specific functionality from the graph.

find_direct_connections: Explores the direct relationships of a functionality within the code graph.

nodes_semantic_search: Semantically searches for code functionalities using natural language.

docs_semantic_search: Semantically searches repository documentation.

get_usage_dependency_links: Analyzes and lists functionalities affected by changes to a code entity.

Prerequisites

Before using the CodeGPT MCP Server, ensure you have:

1. A CodeGPT account (sign up at app.codegpt.co)
2. Uploaded a repository to Code Graph
3. Get your API Key from CodeGPT API Keys page (required).
4. Get your Organization ID (optional) and Graph ID (optional).

Installation

Using npx

Add the following configuration to your MCP client (CodeGPT Extension, Cursor, Copilot, Claude Desktop, Windsurf, etc.):

Adding to Claude Code

Follow these steps to integrate Deep Graph MCP Server with Claude Code.

Quick Setup

claude mcp add "Deep Graph MCP" npx -- -y mcp-code-graph@latest CODEGPT_API_KEY

For team sharing, add the -s project flag:

claude mcp add -s project "Deep Graph MCP" npx -- -y mcp-code-graph@latest CODEGPT_API_KEY

Verification

# Verify installation
claude mcp list

# Get server details
claude mcp get "Deep Graph MCP"

Advanced Workflows with Claude Code Custom Commands

Claude Code supports custom slash commands that combine multiple MCP Code Graph tools for comprehensive analysis workflows.

Setup

Copy the commands directory from this repository to your project root:

cp -r .claude/ /path/to/your/project/

Commit to your project’s git:

git add .claude/commands/
git commit -m "Add custom Claude Code commands for Deep Graph MCP"

Available Commands

Repository-wide analysis commands (no parameters needed):

/project:analyze-architecture          # Complete architectural overview
/project:security-audit               # Comprehensive security analysis
/project:test-coverage-analyzer       # Test coverage and quality analysis
/project:technical-debt-analyzer      # Technical debt assessment
/project:api-ecosystem-analyzer       # Complete API ecosystem analysis
/project:repository-onboarding        # Full repository onboarding guide

Component-specific commands (require parameters):

/project:migration-planner [component/technology]     # Smart migration planning
/project:performance-optimizer [component/function]   # Performance optimization
/project:component-onboarding [component/feature]     # Component-specific training

Usage Examples

/project:analyze-architecture
/project:migration-planner React to Vue.js
/project:performance-optimizer DatabaseService.getUserData
/project:component-onboarding authentication system

📈 Star History

Support

For support and feedback:

• Email: [email protected]
• Website: app.codegpt.co

License

MIT License