lightdash-mcp-server

A MCP(Model Context Protocol) server that accesses to Lightdash

Catalog onlyCatalog onlySTDIO

Overview

lightdash-mcp-server is a Model Context Protocol (MCP) server that provides access to Lightdash's API, enabling AI assistants to interact with Lightdash data through a standardized interface.

To use lightdash-mcp-server, install it via npm, configure your Lightdash API credentials in a .env file, and start the server using the provided commands.

MCP-compatible access to Lightdash's API - Tools for listing projects, spaces, charts, and dashboards - Ability to retrieve custom metrics and catalogs - Support for running examples and development scripts

Integrating AI assistants with Lightdash for data analysis.
Automating project management tasks within Lightdash.
Accessing and manipulating Lightdash data programmatically.

Add to your AI client

Use these steps to connect lightdash-mcp-server 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": {
    "lightdash-mcp-server-syucream": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-lightdash-mcp-server-syucream"
      ]
    }
  }
}

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": {
    "lightdash-mcp-server-syucream": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-lightdash-mcp-server-syucream"
      ]
    }
  }
}

Claude Code

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

.mcp.json (project root)

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

VS Code (Copilot)

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

.vscode/mcp.json

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

Windsurf

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

~/.codeium/windsurf/mcp_config.json

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

Cline

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

Cline MCP Settings (via UI)

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

FAQ

How do I install lightdash-mcp-server?

You can install it using npm with the command: `npm install lightdash-mcp-server`.

What do I need to configure?

You need to create a .env file with your Lightdash API key and URL.

Can I run examples?

Yes! You can run example scripts provided in the examples directory after setting the required environment variables.

Developer tools