The Model Context Protocol (MCP) server for NebulaGraph provides a standardized way to access and interact with NebulaGraph databases. This implementation follows the Model Context Protocol, making it easy to integrate with LLM tooling systems while enabling graph exploration capabilities including schema discovery, queries, and algorithm execution.
Installing the NebulaGraph MCP server is straightforward using pip:
pip install nebulagraph-mcp-server
Before running the server, you need to set up the configuration. The server loads configuration from a .env
file in the working directory.
Create a .env
file with the following parameters:
NEBULA_VERSION=v3 # Currently only v3 is supported
NEBULA_HOST=<your-nebulagraph-server-host>
NEBULA_PORT=<your-nebulagraph-server-port>
NEBULA_USER=<your-nebulagraph-server-user>
NEBULA_PASSWORD=<your-nebulagraph-server-password>
NEBULA_VERSION
must be set to v3
as this is the only supported version currentlyOnce configured, you can start the server by simply running:
nebulagraph-mcp-server
The server will automatically load the configuration from your .env
file and establish a connection to your NebulaGraph instance.
The NebulaGraph MCP server is designed to integrate with LLM tooling systems that support the Model Context Protocol. This enables capabilities like:
You can use the inspector tool to test your MCP server:
npx @modelcontextprotocol/inspector uv run nebulagraph-mcp-server
This will validate that your server is correctly implementing the Model Context Protocol and is ready for integration with compatible systems.
.env
file supportTo add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "nebulagraph-mcp-server" '{"command":"nebulagraph-mcp-server","args":[]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"nebulagraph-mcp-server": {
"command": "nebulagraph-mcp-server",
"args": []
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"nebulagraph-mcp-server": {
"command": "nebulagraph-mcp-server",
"args": []
}
}
}
3. Restart Claude Desktop for the changes to take effect