Model Context Protocol Server for NebulaGraph

Exposes NebulaGraph 3.x through MCP for graph exploration, schema access, and model-driven tooling.

python

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": {
    "nebula-contrib-nebulagraph-mcp-server": {
      "command": "uv",
      "args": [
        "run",
        "nebulagraph-mcp-server"
      ],
      "env": {
        "NEBULA_HOST": "localhost",
        "NEBULA_PORT": "9669",
        "NEBULA_USER": "nebula_user",
        "NEBULA_VERSION": "v3 (set to v3 in your env)",
        "NEBULA_PASSWORD": "secret"
      }
    }
  }
}

You can run this MCP server to access NebulaGraph data through the Model Context Protocol, enabling seamless graph exploration, schema inspection, and quick algorithms while integrating with LLM tooling. It is designed for simple configuration via environment variables and ready-to-use command-line invocation.

How to use

Install and run the NebulaGraph MCP Server to expose NebulaGraph 3.x capabilities through MCP. You can then connect your MCP client to the local server and perform graph exploration, schema queries, and fast graph algorithms. Configure your client to point at the MCP server endpoint you run, and make sure your environment variables provide access to your NebulaGraph instance. The server loads its settings from a .env file or environment variables and starts a local MCP endpoint for your tooling to consume.

How to install

Prerequisites you need before installation:

Python 3.8+ and pip for installing the MCP server package.

pip install nebulagraph-mcp-server

Configuration and run notes

Prepare a .env file or set environment variables to configure the NebulaGraph connection. The server supports these keys:

NEBULA_VERSION=v3 (only v3 is supported at this time)
NEBULA_HOST=<your-nebulagraph-server-host>
NEBULA_PORT=<your-nebulagraph-server-port>
NEBULA_USER=<your-nebulagraph-server-user>
NEBULA_PASSWORD=<your-nebulagraph-server-password>

Run the MCP server. The server is invoked via a command-line interface and will load the configuration from the environment or a .env file.

Examples and quick start

Create a .env file with your NebulaGraph connection details, then start the MCP server from your shell. For a quick start, set the variables and run the server using the standard command line after installation.

Troubleshooting and notes

If you encounter authentication or connection issues, double-check that NEBULA_HOST, NEBULA_PORT, NEBULA_USER, and NEBULA_PASSWORD match your NebulaGraph instance. Ensure NEBULA_VERSION is set to v3 as required. Logs will indicate any misconfigurations or network problems so you can adjust accordingly.

Built by

VeilStrat

AI signals for GTM teams