mcp-server-codegraph
MCP server for graph representation of a codebase
Documentation
mcp-server-codegraph
A Model Context Protocol server that provides tools to generate and query a graph representation in your codebase.
Features
- ๐ Creates a graph representation of your codebase
- ๐ Identifies entities (functions, classes, imports) and their relationships
- ๐ Tracks relationships like function calls, inheritance, and implementations
- ๐ Supports multiple programming languages (Python, JavaScript, Rust)
Tools
- index
- list_file_entities
- list_entity_relationships
Usage
npx @cartographai/mcp-server-codegraph /path/to/directoryClaude Desktop
Add this to your `claude_desktop_config.json`
{
"mcpServers": {
"codegraph": {
"command": "npx",
"args": [
"-y",
"@cartographai/mcp-server-codegraph",
"/path/to/directory",
]
}
}
}Frequently asked questions
What is mcp-server-codegraph?
mcp-server-codegraph is MCP server for graph representation of a codebase
How do I install mcp-server-codegraph?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is mcp-server-codegraph open source?
Yes โ it is hosted on GitHub at https://github.com/CartographAI/mcp-server-codegraph and has 15 stars.
Related MCP tools
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
CTTF: MCP integration between Cursor and Figma, allowing Cursor Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling for the Model Context Protocol. Enhance AI assistants with powerf
The TypeScript AI agent framework. โก Assistants, RAG, observability. Supports any LLM: GPT-4, Claude, Gemini, Llama. Built for the Model Context Protocol to enh
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth! Python-based implementation. Trusted by 11000+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP