code-graph-rag MCP Server

How to use code-graph-rag MCP Server

git clone https://codeberg.org/vitali87/code-graph-rag.git
cd code-graph-rag

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.vitali87/code-graph-rag",
  "title": "Code-Graph-RAG",
  "description": "Graph-based RAG system for multi-language codebases. Parse, index, query, and edit code using knowledge graphs and natural language.",
  "websiteUrl": "https://code-graph-rag.com",
  "repository": {
    "url": "https://codeberg.org/vitali87/code-graph-rag",
    "source": "github"
  },
  "version": "0.0.184",
  "packages": [
    {
      "registryType": "pypi",
      "registryBaseUrl": "https://pypi.org",
      "identifier": "code-graph-rag",
      "version": "0.0.184",
      "runtimeHint": "uvx",
      "transport": {
        "type": "stdio"
      },
      "packageArguments": [
        {
          "type": "positional",
          "value": "mcp-server"
        }
      ],
      "environmentVariables": [
        {
          "name": "ORCHESTRATOR_PROVIDER",
          "description": "LLM provider for the orchestrator agent (openai, anthropic, google, azure, cohere, ollama)",
          "default": "anthropic"
        },
        {
          "name": "ORCHESTRATOR_MODEL",
          "description": "Model name for the orchestrator agent",
          "default": "claude-sonnet-4-20250514"
        },
        {
          "name": "ORCHESTRATOR_API_KEY",
          "description": "API key for the orchestrator LLM provider",
          "isRequired": true,
          "isSecret": true
        },
        {
          "name": "CYPHER_PROVIDER",
          "description": "LLM provider for Cypher query generation (openai, anthropic, google, azure, cohere, ollama)",
          "default": "anthropic"
        },
        {
          "name": "CYPHER_MODEL",
          "description": "Model name for Cypher query generation",

What is code-graph-rag MCP Server?

code-graph-rag is a Python MCP server with uvx/pip, docker, git clone. The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.

Key capabilities

• Tool access support
• Shell commands support
• File editing support
• Document generation support
• OpenAI provider support
• Anthropic provider support
• Google provider support

Available tools

Technical details

Install or run code-graph-rag using uvx/pip. Check vitali87/code-graph-rag for the latest setup command.

• Built for Python
• Built for Node.js
• Built for Docker
• Built for Go
• Built for Rust
• Install or run with uvx/pip
• Install or run with docker
• Install or run with git clone

Requirements and access

Security and permissions

Review permissions before connecting any MCP server to an agent. Pay special attention to whether it can read local files, write data, call external services, or perform destructive actions.

When to use code-graph-rag MCP Server

• Use it for connecting agents to external tools and data.
• Use it for integrations workflows.
• Use it for coding workflows.
• Use it for data workflows.

Built with

Explore related resources

Frequently asked questions