graphify
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Graphify is an MCP server that transforms codebases into queryable knowledge graphs using local AST parsing. It extracts relationships from code, documentation, SQL schemas, PDFs, and other project artifacts without requiring embeddings or vector stores. Developers can query the graph using natural language questions, trace connections between entities, and explore architecture through an interactive visualization, all while keeping code analysis fully local with tree-sitter AST parsing.
Key Features
Use Cases
- 01Query codebase architecture with natural language instead of grepping files
- 02Trace dependencies and relationships between functions, classes, and modules across files
- 03Onboard new developers by visualizing how components connect and interact
- 04Identify god nodes and surprising cross-module connections during refactoring
- 05Extract design rationale from inline comments and link them to code entities
- 06Review PR impact by analyzing which graph communities are affected by changes
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
graphify — FAQ
What is Graphify?+
Graphify is an MCP server that parses your codebase into a knowledge graph using local AST analysis. It lets AI assistants query code relationships, trace paths between entities, and understand architecture without reading raw files.
How do I install the Graphify MCP server?+
Install via uv or pipx (`uv tool install graphifyy`), build a graph with `graphify extract .`, then run `python -m graphify.serve graphify-out/graph.json` to start the MCP stdio server. Point your MCP client at this command.
Which AI clients work with Graphify?+
Graphify works as an MCP server with any MCP-compatible client. It also provides native skill integrations for Claude Code, Cursor, Codex, Gemini CLI, GitHub Copilot, Aider, and 15+ other AI coding assistants.
Do I need API keys to use Graphify?+
No API keys are required for code-only extraction—it runs fully offline with tree-sitter. API keys (Anthropic, Gemini, OpenAI, etc.) are only needed if you want to extract semantic information from docs, PDFs, images, or videos.
Is Graphify free and open source?+
Yes, Graphify is open source (GitHub: Graphify-Labs/graphify) and free to use. The PyPI package is `graphifyy` with no telemetry or usage tracking.
How do I query the knowledge graph?+
Use `graphify query "<question>"` for natural language queries, `graphify path A B` to trace connections between entities, or `graphify explain "NodeName"` for details. The MCP server exposes these as structured tools for AI assistants.
How do I install graphify?+
Open the source repository on GitHub and follow its README. graphify is a mcp server — MCP Agents Market links you directly to the official repo.
Is graphify free?+
graphify is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.