drio
Open app

Model Context Protocol Server for NebulaGraph

Source

Model Context Protocol Server for NebulaGraph 3.x

Catalog onlyCatalog onlySTDIO

Overview

The Model Context Protocol Server for NebulaGraph is an implementation that provides seamless access to NebulaGraph 3.x, allowing users to explore graph data and integrate with LLM tooling systems.

To use the server, install it via pip and configure it using environment variables or a .env file. The command nebulagraph-mcp-server will load the necessary configurations.

  • Seamless access to NebulaGraph 3.x. - Support for schema exploration, querying, and shortcut algorithms. - Follows the Model Context Protocol for integration with LLM tools. - Simple command-line interface with environment variable support.
  1. Integrating graph databases with machine learning models.
  2. Exploring complex graph structures and relationships.
  3. Developing applications that require graph data manipulation and analysis.

Add to your AI client

Use these steps to connect Model Context Protocol Server for NebulaGraph in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "nebulagraph-mcp-server-psiace": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "nebulagraph-mcp-server-psiace": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "nebulagraph-mcp-server-psiace": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "nebulagraph-mcp-server-psiace": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "nebulagraph-mcp-server-psiace": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "nebulagraph-mcp-server-psiace": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-nebulagraph-mcp-server-psiace"
      ]
    }
  }
}

FAQ

What version of NebulaGraph is supported?

Only NebulaGraph version 3 is supported at this time.

How do I install the server?

You can install it using the command: `pip install nebulagraph-mcp-server`.

Can I configure the server using a .env file?

Yes, the server supports configuration via environment variables and .env files.

Developer tools