CodeGraphContext/CodeGraphContext

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

What it solves

CodeGraphContext (CGC) addresses the limitation of plain text search and simple RAG (Retrieval-Augmented Generation) when analyzing large codebases. While grep or chunk-based retrieval can find strings, they often miss the structural relationships—such as call chains, class hierarchies, and module boundaries—that are essential for deep repository-wide reasoning.

How it works

CGC parses source code using Tree-sitter and optional SCIP indexers to extract symbols, functions, classes, and their relationships. It then stores this data in a graph database (supporting backends like FalkorDB, KuzuDB, or Neo4j). This structured knowledge graph can then be queried via a standalone CLI toolkit for developers or exposed to AI assistants through a Model Context Protocol (MCP) server, allowing AI agents to understand the actual connectivity of the code.

Who it’s for

It is designed for developers and AI agent creators who need to perform complex code analysis, such as tracing call chains across files, identifying dead code, or providing AI assistants with high-precision structural context of a repository.

Highlights

  • Dual Mode: Operates as both a CLI toolkit for manual analysis and an MCP server for AI agents.
  • Multi-Language Support: Supports 23 programming languages, including Python, JS/TS, Java, C++, Rust, and Solidity.
  • Flexible Backends: Compatible with multiple graph databases, including embedded options for zero-config local setup.
  • Live Watching: Automatically updates the graph in real-time as files change using cgc watch.
  • Pre-indexed Bundles: Allows instant loading of famous repositories via .cgc bundles without needing to re-index.

Related

  • Project
    forloopcodes/contextplus

    An MCP server that turns large codebases into searchable, hierarchical feature graphs using RAG, AST parsing, and spectral clustering for high-accuracy AI coding context.

  • Project
    johnhuang316/code-index-mcp

    An MCP server that provides intelligent code indexing and AST-based analysis to help AI assistants navigate and understand complex codebases.

  • Project
    justrach/codedb

    A high-performance code intelligence server for AI agents that provides structural indexing and fast symbol search to help agents understand large codebases.

  • Project
    Muvon/octocode

    A structural code intelligence tool that transforms codebases into knowledge graphs via an MCP server, enabling AI agents to navigate dependencies and perform semantic search.

  • Project
    colbymchenry/codegraph

    A semantic code intelligence platform that builds a local knowledge graph of a codebase to provide AI agents with surgical context, reducing token costs and tool calls.