Apache AGE

MCP Server for Apache AGE

python

2

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "veloper-agemcp": {
      "command": "agemcp",
      "args": [
        "run"
      ]
    }
  }
}

You manage multiple graphs in Apache AGE through an MCP server that exposes actions for creating, updating, administering, and visualizing graphs. This server acts as a centralized orchestrator for graph data and enables AI agents to interact with your AGE graphs in a consistent, scalable way.

How to use

You interact with the MCP server through a client that talks to the server, enabling you to manage graphs, vertices, and edges. Core actions include creating or getting graphs, upserting vertices and edges non-destructively, listing graphs, dropping graphs, and generating visualizations. Use these capabilities to build dynamic, graph-based workflows for AI agents, data exploration, and graph analytics.

How to install

Prerequisites: you need a working Python environment and a Postgres instance for Apache AGE. You also need a CLI tool to run the MCP server.

Install the MCP server package with the recommended tool.

pipx install agemcp

Additional notes

Configure the MCP server to point at your Postgres AGE database using the provided config flow, then start the server to begin accepting MCP requests.

Start the server process with the runtime command shown in examples.

Available tools

get_or_create_graph

Get or create a graph with the specified name.

list_graphs

List all graph names in the database.

upsert_graph

Upsert both vertices and edges into the specified graph (deep merge).

upsert_edge

Insert or update an edge's properties in a graph non-destructively.

upsert_vertex

Insert or update a vertex's properties in a graph non-destructively.

drop_graphs

Drop one or more graphs by name.

drop_vertex

Remove a vertex by ident.

drop_edge

Remove an edge by ident.

generate_visualization

Generate a single-page HTML file visualizing a graph using vis.js and pyvis.