JudiniLabs MCP Code Graph

Provides an MCP interface to interact with Deep Graph code graphs via multiple tools and commands.

typescript

371

GitHub Stars

typescript

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "judinilabs-mcp-code-graph": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-code-graph@latest",
        "username/repository-name",
        "username2/repository-name2"
      ],
      "env": {
        "CODEGPT_ORG_ID": "YOUR_ORG_ID",
        "CODEGPT_API_KEY": "YOUR_API_KEY",
        "CODEGPT_GRAPH_ID": "YOUR_GRAPH_ID"
      }
    }
  }
}

This MCP server gives you a ready-made interface to interact with Deep Graph code graphs from your CodeGPT account or public graphs. It exposes a set of graph-based tools you can invoke through compatible MCP clients to explore, query, and analyze code functionality within repositories and their documentation.

How to use

Connect to the Deep Graph MCP Server from your MCP client (CodeGPT Extension, Cursor, Copilot, Claude, Windsurf, Gemini CLI, or others). You will run the server via a standard MCP command and then call the provided tools to list graphs, fetch code snippets, explore relationships, and perform semantic searches across code and docs.

How to install

Prerequisites you need before installation:

Install Node.js or ensure it is available in your environment. You typically already have npm when you install Node.js.

Use npx to pull the MCP server and configure your client. The common installation pattern is shown below as a ready-to-run configuration snippet.

Install for public graphs (no CodeGPT account required) using the following configuration in your MCP client settings.

Additional setup and configuration

Two MCP server configurations are available: one for public graphs and one for private graphs. Use the public graphs configuration if you simply want to explore public repositories. If you have a CodeGPT account and private graphs, use the private graphs configuration and supply your API key, organization ID, and graph ID.

Public graphs configuration (no account required): you run the MCP with npx and specify the repository references you want to load.

Private graphs configuration (CodeGPT account required): you run the MCP with npx and pass API key, organization ID, and graph ID as arguments.

Usage notes

Both configurations are designed to be used with any MCP client that supports JSON-based MCPServer definitions. Ensure you provide the correct repository references and authentication details where required. You can add more repositories if needed.

Examples of available capabilities

List available graphs, retrieve complete code for a function, explore direct connections in the code graph, perform semantic searches on code and docs, and analyze usage dependencies and folder structures within a repository.

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.

folder-tree-structure

Retrieves the tree structure of a folder in the repository.

Built by

VeilStrat

AI signals for GTM teams