lightdash-mcp-server

This project is a Model Context Protocol (MCP) server designed to provide access to Lightdash data. It enables AI assistants to interact with Lightdash through a standardized MCP interface.

Features

The server offers several tools for interacting with Lightdash, including: listing projects, retrieving project details, listing spaces, charts, and dashboards, fetching custom metrics, and obtaining catalog information. It also supports retrieving charts and dashboards as code.

Quick Start

Installation

Installation can be done automatically via Smithery using npx -y @smithery/cli install lightdash-mcp-server --client claude or manually using npm install lightdash-mcp-server.

Configuration

Configuration requires setting the LIGHTDASH_API_KEY (your Lightdash PAT) and LIGHTDASH_API_URL (the API base URL) as environment variables.

Usage

To start the server, use npx lightdash-mcp-server. The MCP configuration JSON needs to be edited to include the server command, arguments, and environment variables.

Development

Available Scripts

Development scripts include: npm run dev for development mode, npm run build for production build, npm run start to start the production server, npm run lint for linting, npm run fix to fix linting issues, and npm run examples to run example scripts.

Contributing

Contributions are welcome. Fork the repository, create a feature branch, run tests and linting (npm run lint), commit changes, push to the branch, and create a pull request.