Lightdash

Provides MCP-compatible access to Lightdash data and actions (projects, spaces, charts, dashboards, catalogs, and metrics).

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-syucream_lightdash-mcp-server": {
      "command": "npx",
      "args": [
        "lightdash-mcp-server"
      ],
      "env": {
        "LIGHTDASH_API_KEY": "your_api_key",
        "LIGHTDASH_API_URL": "https://app.lightdash.cloud/api/v1"
      }
    }
  }
}

This MCP server provides a standardized, MCP-compatible way to access Lightdash data. You can query projects, spaces, charts, dashboards, and custom metrics from Lightdash through a consistent interface, enabling AI assistants to work with your Lightdash data more effectively.

How to use

You will run the MCP server locally or in your environment and connect to it with an MCP client. Once the server is running, you can list projects, inspect project details, retrieve catalog information, and fetch charts and dashboards as code, among other data retrieval tasks. Use the available MCP endpoints to integrate Lightdash data into your AI workflows without manually calling Lightdash APIs.

How to install

Prerequisites you need before installation:

Node.js and npm installed on your machine. You can verify by running node -v and npm -v in your terminal.

npm install lightdash-mcp-server

Configuration and start

Create a configuration file containing your Lightdash credentials. The server reads these credentials from environment variables. Create a file named .env in your project directory with the following keys.

LIGHTDASH_API_KEY=your_api_key
LIGHTDASH_API_URL=https://app.lightdash.cloud/api/v1  # or your custom Lightdash instance URL

Run the MCP server

Start the MCP server using the runtime command shown. This will launch the server so you can connect your MCP client and begin requesting Lightdash data.

npx lightdash-mcp-server

Example client setup for local testing

When testing locally, you can provide credentials via environment variables or a local .env file. For example, you may expose the required keys to your client environment and run any example scripts that demonstrate typical tool usage.

# Example usage for client-side testing (adjust per your setup)
export EXAMPLES_CLIENT_LIGHTDASH_API_KEY=your_api_key
export EXAMPLES_CLIENT_LIGHTDASH_PROJECT_UUID=your_project_uuid
npm run examples

Available tools

list_projects

Query and return all projects in your Lightdash organization.

get_project

Fetch details for a specific Lightdash project by UUID or identifier.

list_spaces

List all spaces within a given project.

list_charts

Retrieve all charts associated with a project.

list_dashboards

Retrieve all dashboards associated with a project.

get_custom_metrics

Get custom metrics defined for a project.

get_catalog

Obtain the catalog for a project to understand data assets and schemas.

get_metrics_catalog

Fetch the metrics catalog for a project.

get_charts_as_code

Return charts in code form for a project.

get_dashboards_as_code

Return dashboards in code form for a project.