Lightdash

You can expose Lightdash data to AI assistants through an MCP server that implements the Model Context Protocol. This server lets you list projects, spaces, charts, dashboards, and catalogs, and obtain code representations of charts and dashboards, all through a standardized interface you can connect to from your MCP clients.

How to use

Connect your MCP client to the Lightdash MCP server using either the built-in stdio transport (default) or the Streamable HTTP transport. With stdio, you run the server locally and pass the command to the client configuration. With HTTP, you run the server on a port and point your client to the HTTP endpoint.

How to install

Prerequisites you need on your machine: a recent version of Node.js (and npm) to install and run the MCP server.

Install via Smithery (automatic for Claude Desktop):

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

Manual installation (local):

npm install lightdash-mcp-server

Configuration and usage notes

Set the API credentials and endpoint for Lightdash to allow the MCP server to access Lightdash data.

Two transport modes are supported: stdio (default) and HTTP.

Available tools

list_projects

List all projects in the Lightdash organization.

get_project

Get details of 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 custom metrics for a project.

get_catalog

Get catalog for a project.

get_metrics_catalog

Get metrics catalog for a project.

get_charts_as_code

Get charts as code for a project.

get_dashboards_as_code

Get dashboards as code for a project.