Happy slice of mcp pizzaMCP.pizza

CodeGraph

MCP.Pizza Chef: codegraph-ai

CodeGraph creates a rich, interactive map of your entire codebase, including functions, classes, imports, and call chains. It works with popular editors like VS Code and Cursor, supporting 38 programming languages. Without needing API keys, it helps AI assistants quickly understand and navigate your code, replacing slow manual searches. Setup involves adding a small config snippet or installing an extension, making it accessible for non-developers using supported apps.

Coding
Other

Use This MCP server To

Explore my codebase’s functions and classes visually Find where functions are called across files Get AI help understanding complex code relationships Review pull requests with automatic code analysis Use AI to navigate code in VS Code or Cursor Index multiple projects for cross-referencing Skip manual grep searches with semantic code queries

README

CodeGraph

Cross-language code intelligence for AI agents and developers.

License

CodeGraph builds a semantic graph of your codebase — functions, classes, imports, call chains — and exposes it through 42 MCP tools, a VS Code extension, a JetBrains IDE plugin, and a persistent memory layer. Parses 38 languages via tree-sitter. AI agents get structured code understanding instead of grepping through files.

Quick Start

MCP Server (Claude Code, Cursor, any MCP client)

Add to ~/.claude.json (or your MCP client config):

{
  "mcpServers": {
    "codegraph": {
      "command": "/path/to/codegraph-server",
      "args": ["--mcp"]
    }
  }
}

The server indexes the current working directory automatically.

VS Code Extension

Install the VSIX:

code --install-extension codegraph-0.20.1.vsix

One VSIX serves every platform. The analysis engine is not bundled: on first activation the extension offers to download the engine built for your platform, verifies it against the published checksum, and installs it into ~/.codegraph/bin - the same location the JetBrains plugin uses, so one download serves both. The download is offered rather than performed automatically, because it is a native binary that runs with your permissions. Decline it and run CodeGraph: Download Analysis Engine from the command palette whenever you are ready.

Once an engine is present, the extension starts it automatically and registers all tools as Language Model Tools for Copilot.

JetBrains IDEs

A plugin for IntelliJ IDEA, PyCharm, GoLand, Android Studio and the rest of the family drives the same engine over LSP: Code Vision, Symbols and Memories tool windows, a graph panel, and one-click MCP registration for the AI Assistant. It resolves or downloads the engine the same way the VS Code extension does, sharing ~/.codegraph/bin.

CodeGraph FAQ

Can I use CodeGraph to understand and navigate my codebase faster?
Yes — CodeGraph builds a detailed map of your code’s functions, classes, and calls, making it easy for AI assistants to help you explore and understand your code across 38 languages.
Can I use CodeGraph with VS Code or Cursor?
Yes — it supports VS Code, Cursor, Cline, Windsurf, and other MCP-compatible clients.
Do I need an API key or account to use CodeGraph?
No — CodeGraph runs locally and does not require any API keys or accounts.
How hard is it to set up CodeGraph?
Setup is straightforward — you just add a small config snippet to your MCP client settings or install the VS Code extension.
Can CodeGraph analyze multiple projects or directories?
Yes — you can configure it to index multiple directories or exclude certain folders as needed.
Does CodeGraph work with AI models like Claude, Cursor, and Gemini?
Yes — it is designed to enhance AI agents including Claude, Cursor, Windsurf, Codex, and Cline for better code understanding.