Lightdash MCP Server

🚀 Lightdash-MCP-Server

This is a MCP (Model Context Protocol) server for accessing Lightdash. It provides MCP-compatible access to the Lightdash API through a standardized interface, enabling AI assistants to interact with your Lightdash data.

✨ Features

Available tools:

• list_projects - List all projects in the Lightdash organization.
• get_project - Get detailed information about a specific project.
• list_spaces - List all spaces in a project.
• list_charts - List all charts in a project.
• list_dashboards - List all dashboards in a project.
• get_custom_metrics - Get the custom metrics of a project.
• get_catalog - Get the catalog structure of a project.
• get_metrics_catalog - Get the metrics catalog of a project.
• get_charts_as_code - Get the code representation of charts in a project.
• get_dashboards_as_code - Get the code representation of dashboards in a project.

🚀 Quick Start

📦 Installation

Install via Smithery

To automatically install the Lightdash MCP Server for Claude Desktop via Smithery:

npx -y @smithery/cli install lightdash-mcp-server --client claude

Manual Installation

npm install lightdash-mcp-server

Configuration

• LIGHTDASH_API_KEY: Your Lightdash PAT (Personal Access Token).
• LIGHTDASH_API_URL: The base URL of the API.

💻 Usage Examples

Basic Usage

1. Start the MCP server.

Run directly:

npx lightdash-mcp-server

Or run the installed module using Node.js.

2. Edit your MCP configuration JSON file and add the following content:

...
    "lightdash": {
      "command": "npx",
      "args": [
        "-y",
        "lightdash-mcp-server"
      ],
      "env": {
        "LIGHTDASH_API_KEY": "<your PAT>",
        "LIGHTDASH_API_URL": "https://<your base URL>"
      }
    },
...

🔧 Technical Details

Available Scripts

• npm run dev - Start the server in development mode with hot reloading.
• npm run build - Build the project for production.
• npm run start - Start the production server.
• npm run lint - Run code checks (ESLint and Prettier).
• npm run fix - Automatically fix code issues.
• npm run examples - Run example scripts.

Contribution Guidelines

1. Fork the repository.
2. Create a feature branch.
3. Run tests and code checks: npm run lint.
4. Commit your changes.
5. Push to the branch.
6. Create a Pull Request.