CodeGraphContext

CodeGraphContext is an MCP server and CLI toolkit that indexes local code into a graph database to provide context for AI assistants.

CodeGraphContext is a CLI toolkit and Model Context Protocol (MCP) server designed to index local code into a fully navigable graph database. It analyzes code components, relationships, and dependencies, allowing AI assistants to query the codebase using natural language. The tool watches local files for changes and automatically updates the graph in real time during development. It supports inputs such as local folders, ZIP files, CGC bundles, and public GitHub or GitLab repositories. Using FalkorDB Lite as the default database, with Neo4j available via Docker or native installation, it is built for developers wanting deep codebase understanding and cross-repository navigation. The project is released under the MIT License and requires Python 3.10 or newer.

CodeGraphContext at a glance

Best for: Software engineer
Runs on: CLI, VS Code, API
Pricing: Free
Released: August 2025
Category: AI coding tool
Website: cgc.codes

Key features

Indexes code into a knowledge graph
Analyzes code relationships and dependencies
Watches local files for live updates
Provides a command-line setup wizard
Integrates with AI IDEs via MCP server
Supports public GitHub and GitLab repositories
Queries call chains and class hierarchies

Use it for

Querying codebases with natural language via AI assistants
Finding direct and indirect function calls across directories
Tracking code dependencies and project hierarchies
Detecting dead code and complex functions

Alternatives to CodeGraphContext

Codebase Memory MCP — High-speed indexing and persistent knowledge graphs for AI coding agents.
CodeSight — Reduces AI token usage significantly and maps projects instantly.
Context7 — Provides up-to-date documentation for AI agents and code editors.
Code Review Graph — Provides a median 63x context reduction while keeping all code processing local.
ContextMCP — Maintains fresh, accurate context for AI agents using AST-aware chunking.
Context Mode — Saves up to 98 percent of context per session by keeping raw data out of the LLM.
Axiomcodegraph — Resolves calls from types rather than syntax for higher accuracy.
Claude Context — It reduces token costs and provides deep context for large codebases.
Context Engineering Kit — Improves agent reliability and code generation quality with minimal token footprint.
Cody — Provides complete codebase context for developers and AI agents at scale.
ContextStream — It maintains project context and history to reduce agent errors.
Official MCP Servers — Find trusted official MCP servers without unofficial forks or abandoned projects.

All CodeGraphContext alternatives