CodeGraphContext - An MCP server that converts your codebase into a graph database, enabling AI assistants and humans to retrieve precise, structured context

## CodeGraphContext- the go to solution for graph based code indexing It's an MCP server that understands a codebase as a **graph**, not chunks of text. Now has grown way beyond my expectations - both technically and in adoption. ### Where it is now - **v0.2.7 released** - ~**1.1k GitHub stars**, ~**325 forks** - **50k+ downloads** - **75+ contributors, ~150 members community** - Used and praised by many devs building MCP tooling, agents, and IDE workflows - Expanded to 14 different Coding languages ### What it actually does CodeGraphContext indexes a repo into a **repository-scoped symbol-level graph**: files, functions, classes, calls, imports, inheritance and serves **precise, relationship-aware context** to AI tools via MCP. That means: - Fast *“who calls what”, “who inherits what”, etc* queries - Minimal context (no token spam) - **Real-time updates** as code changes - Graph storage stays in **MBs, not GBs** It’s infrastructure for **code understanding**, not just 'grep' search. ### Ecosystem adoption It’s now listed or used across: PulseMCP, MCPMarket, MCPHunt, Awesome MCP Servers, Glama, Skywork, Playbooks, Stacker News, and many more. - Python package→ https://pypi.org/project/codegraphcontext/ - Website + cookbook → https://codegraphcontext.vercel.app/ - GitHub Repo → https://github.com/CodeGraphContext/CodeGraphContext - Docs → https://codegraphcontext.github.io/ - Our Discord Server → https://discord.gg/dR4QY32uYQ This isn’t a VS Code trick or a RAG wrapper- it’s meant to sit **between large repositories and humans/AI systems** as shared infrastructure. Happy to hear feedback, skepticism, comparisons, or ideas from folks building MCP servers or dev tooling.