Connect the graph MCP server

The graph MCP server reads a Graphify graph and exposes exploration tools to compatible clients. Start by building graphify-out/graph.json using the quickstart.

Install the MCP extra

uv tool install "graphifyy[mcp]"

This installs the graphify-mcp executable into the same tool environment as Graphify. If uv reports an existing installation without the extra, reinstall with uv tool install --reinstall "graphifyy[mcp]".

Configure a local client

Use an absolute path to the graph. GUI apps often start with a different working directory from your terminal.

Claude Code
Cursor
Codex
Other clients

claude mcp add --transport stdio graphify -- graphify-mcp /absolute/path/to/repo/graphify-out/graph.json

Add a server entry to your user or project MCP configuration:

{
  "mcpServers": {
    "graphify": {
      "command": "graphify-mcp",
      "args": ["/absolute/path/to/repo/graphify-out/graph.json"]
    }
  }
}

codex mcp add graphify -- graphify-mcp /absolute/path/to/repo/graphify-out/graph.json

Or configure the equivalent server in Codex’s MCP settings.

Choose the stdio transport, set the command to graphify-mcp, and pass the absolute graph path as the first argument. If the client cannot find the executable, replace it with the absolute path to graphify-mcp in your installed tool environment.For client-specific setup, visit the Graphify MCP connection guide. Choose your client there for its configuration instructions. That page also covers the hosted Graphify Cloud endpoint; the stdio setup above connects to a graph on your own machine.

Check the connection

Refresh your client’s MCP connections. Ask it to call graph_stats first, then query_graph with a question about the repository. The tool reference lists the current schemas.

{"question": "authentication flow", "token_budget": 1500}

Python environment alternative

If you installed Graphify into a virtual environment, activate that environment first, then run:

python -m graphify.serve /absolute/path/to/repo/graphify-out/graph.json

Use the interpreter where the MCP extra is installed. In a GUI client, set the command to that interpreter’s absolute path. Your shell’s Python can differ from uv’s tool environment.

Scope of the tools

Graph exploration tools retrieve the saved graph. The PR tools additionally read GitHub context through gh; they are not an entirely offline workflow. MCP triage_prs returns data for the calling assistant to reason over. To share a graph through a URL, use the HTTP server guide. To search Graphify’s documentation instead of your code graph, use the docs search MCP.

​Install the MCP extra

​Configure a local client

​Check the connection

​Python environment alternative

​Scope of the tools

Install the MCP extra

Configure a local client

Check the connection

Python environment alternative

Scope of the tools