The Lightdash MCP Server provides a standardized interface for AI assistants to interact with Lightdash data. With this server, you can:
List all projects in the Lightdash organization
Get details of a specific project by UUID
List all spaces, charts, and dashboards in a project
Retrieve custom metrics, catalog, and metrics catalog
Fetch charts and dashboards as code
Get metadata and analytics for specific tables in the data catalog
Retrieve organization user attributes
Used for configuration management by storing Lightdash API credentials in environment variables.
Provides code linting functionality for development and contributing to the project.
Used for package installation, dependency management, and running scripts for the server.
Handles code formatting to maintain consistent style across the codebase.
lightdash-mcp-server
A MCP(Model Context Protocol) server that accesses to Lightdash.
This server provides MCP-compatible access to Lightdash's API, allowing AI assistants to interact with your Lightdash data through a standardized interface.
Features
Available tools:
list_projects- List all projects in the Lightdash organizationget_project- Get details of a specific projectlist_spaces- List all spaces in a projectlist_charts- List all charts in a projectlist_dashboards- List all dashboards in a projectget_custom_metrics- Get custom metrics for a projectget_catalog- Get catalog for a projectget_metrics_catalog- Get metrics catalog for a projectget_charts_as_code- Get charts as code for a projectget_dashboards_as_code- Get dashboards as code for a project
Related MCP server: Astro Docs MCP Server
Quick Start
Installation
Installing via Smithery
To install Lightdash MCP Server for Claude Desktop automatically via Smithery:
Manual Installation
Configuration
Create a .env file with your Lightdash API credentials:
Usage
Start the MCP server.
Directly:
Or, run the installed module with node.
Edit your MCP configuration json:
Development
Available Scripts
npm run dev- Start the server in development mode with hot reloadingnpm run build- Build the project for productionnpm run start- Start the production servernpm run lint- Run linting checks (ESLint and Prettier)npm run fix- Automatically fix linting issuesnpm run examples- Run the example scripts
Contributing
Fork the repository
Create your feature branch
Run tests and linting:
npm run lintCommit your changes
Push to the branch
Create a Pull Request