MCP servers

Graphify-Labs/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.

Stars
151,645
+7 days
—
Forks
14,568
Language
Python
License
Apache-2.0
Last push
21 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This tool turns codebases, documentation, schemas, and media into a queryable knowledge graph without relying on vector embeddings. It parses code locally using tree-sitter abstract syntax trees and tags every edge as either extracted or inferred. Developers can inspect architecture, run graph queries, trace shortest paths, and register the skill in Claude Code and other assistants.

Use it when

  • Map a large codebase into an interactive knowledge graph without sending source code to an LLM
  • Trace dependencies or connections between two components instead of grepping multiple files
  • Guide Claude Code to query structured graph relationships before reading raw source files

Install

pip
uv tool install graphifyy
pip
pipx install graphifyy

Commands quoted from the repo's README. Read the README before running them.

Needs a token or API key.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.