workflowstacks
mcp-server

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.
126,241 stars+1,914★ this week12,183 forksPythonUpdated 10/13/2026100% free · open source
What it does

It builds a deterministic, query‑able knowledge graph of your entire codebase—including source files, docs, SQL schemas, configs and PDFs—so AI assistants can answer exact, code‑level questions without using a vector store.

When to use it
  • •You need an LLM to answer precise “where is X defined?” or “which endpoints touch this table?” questions across a large monorepo.
  • •Your team wants to embed a live code‑graph into Claude Code, Cursor, Codex or Gemini prompts for real‑time debugging or impact analysis.
  • •You must keep the graph up‑to‑date automatically as code changes, without relying on fuzzy vector similarity.
Ready-to-paste prompt
In Claude Code, you can now write:
```
@graphify "Give me all Python functions that write to the `orders` table and are referenced in the API docs. Return the file path and line numbers."
```
Heads up: Graphify requires Python 3.10+ **and** GraphViz installed on the host (e.g., `brew install graphviz` or `apt-get install graphviz`); without GraphViz the AST‑edge visualizer and PDF parsing will fail.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

✅ Light setup

Installs with a command or two; your AI agent can do it for you.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/graphify && curl -fsSL https://workflowstacks.com/api/skills/graphify/claude-skill -o ~/.claude/skills/graphify/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How graphify works
Codeflow
Free to inspect

Graphify is a very large Python project (~64k lines across 104 code files, plus 315 test files). Setup is light: installs like a normal app. Reading the code is optional. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~64k lines · 104 code files · days to read — use, don't read
Setup
One-command install
Installs like a normal app. Reading the code is optional.
Runs on
Python · Docker
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    graphify/cli.py
    Where the program starts running
  4. 4
    pyproject.toml
    Dependencies and the commands it exposes
  5. 5
    graphify/__init__.py
    Inside graphify/ — the main logic begins here
What's in each folder
graphify/Core code — the actual logic221 files
docs/Documentation41 files
tools/Helper scripts174 files
worked/Folder36 files
scripts/Helper scripts1 files
tests/Tests — proof it works364 files
.github/CI / automation (GitHub Actions)4 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
Graphify-Labs
Language
Python
Category
mcp-server
Published
4/3/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/graphify.svg)](https://workflowstacks.com/skills/graphify?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

MCP config

Context7 (live docs) MCP config

Pull up-to-date library docs into Claude so it codes against the real API.

MCP config

GitHub MCP config

Search repos, read code, open issues and PRs from Claude.

MCP config

Memory (knowledge graph) MCP config

Persistent memory across chats via a local knowledge graph.

Related skills

More mcp-server tools founders pair with this one.

mcp-server★ 226,471
Rea: Reverse Engineer Apps
Inspect apps down to binary level with Rea. For founders needing code clarity.
mcp-server★ 155,573
open-webui: Self‑hosted AI Chat UI for Faster LLM Integration
Launch a sleek, web‑based AI interface that works with Ollama, OpenAI API, and more—ideal for founders needing a quick, customizable LLM front‑end. 153k+ GitHub stars.
mcp-server★ 107,332
gemini-cli: Supercharge Your Terminal with Gemini AI
Leverage the Gemini AI directly from your command line to accelerate decision‑making and prototyping. Ideal for tech founders who need instant, code‑native insights.
mcp-server★ 226
Jumpstarter: Simplify Hardware Testing
Founders get easy hardware testing for software. For those using automation and embedded systems.
mcp-server★ 88,423
worldmonitor: Real‑time Global Insight Dashboard for Founders
Gain instant situational awareness with AI‑curated news, geopolitics, and infrastructure data—all in one TypeScript dashboard. Ideal for founders needing fast, reliable OSINT.
mcp-server★ 4,989
MockServer: Easy API Mocking
Get easy mocking of systems via HTTP/HTTPS with MockServer, ideal for startup founders integrating with multiple services, backed by 4.9k+ GitHub stars