Skip to main content
graphify-mcp reads graphify-out/graph.json and exposes it as MCP tools. Your agent can then ask for a subgraph, a node, a path, or the pull requests a change affects, instead of reading files to find out.
Use the MCP server when your client supports MCP but not skills, or when several people or agents should read one graph. For a graph hosted and refreshed for you, use the hosted MCP server.

Before you start

Build a graph first with the CLI quickstart, then install the MCP extra:

Connect one agent over stdio

Use an absolute path. GUI clients often start in a different folder from your terminal.

Serve a team over HTTP

Clients send the key as Authorization: Bearer <key> or X-API-Key: <key>. A request without it gets 401. The server binds to 127.0.0.1 by default and warns if you bind 0.0.0.0 without a key.

Tools your agent gets

The server also publishes resources such as graphify://report (the GRAPH_REPORT.md text) and graphify://god-nodes.

Verify the connection

Reload MCP servers in your client and ask it to call graph_stats. Then try:
For HTTP, check the endpoint from a terminal:
A 200 means the server is up and your key works.
The MCP extra isn’t installed in the environment on your PATH. Run uv tool install --reinstall "graphifyy[mcp]", or use python -m graphify.serve from the virtual environment where Graphify is installed.
Yes. It reloads graph.json when the file changes, so graphify update . or a git hook keeps answers current.

What’s next

Self-host with Docker

Run the HTTP server in a container.

Vibe coding with Graphify Local

Make your agent use the graph by default.

Try it in Graphify

We build and host the graph for you. Start with a 14-day Pro trial, then keep up to 3 repositories on Free. No card required.