MCP Catalogs
Home

lightdash_mcp

by poddubnyoleg·19·Score 43

MCP server connecting AI assistants to Lightdash analytics platform for data discovery and visualization management.

ai-llmdeveloper-toolsproductivity
6
Forks
0
Open issues
2 mo ago
Last commit
2d ago
Indexed

Overview

The lightdash_mcp server provides a comprehensive interface for AI assistants to interact with Lightdash, a modern data analytics platform. It exposes tools for data catalog exploration, chart creation and management, dashboard organization, and query execution. The server supports multiple authentication methods including standard API tokens, Cloudflare Access, and Google Cloud Identity-Aware Proxy, making it suitable for various deployment scenarios.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI assistants analyzing business data by exploring tables and creating visualizations
you:Automating dashboard creation and management through natural language instructions
you:Generating ad-hoc data queries based on conversational analysis needs
you:How do I get my Lightdash Personal Access Token?
you:Can I use this MCP server with self-hosted Lightdash?

When to choose this

Choose this server if you're already using Lightdash for analytics and want AI assistants to programmatically explore your data, create visualizations, and manage dashboards without leaving your conversational interface.

When NOT to choose this

Avoid this server if you're not using Lightdash or need to connect to other analytics platforms, as it's specifically designed for Lightdash integration only.

Tools this server exposes

12 tools extracted from the README
  • list-projects

    List all available Lightdash projects

  • get-project

    Get detailed information about a specific project

  • list-explores

    List all available explores/tables in a project

  • get-explore-schema

    Get detailed schema for a specific explore

  • create-chart

    Create a new saved chart with metric query and visualization config

  • get-chart-details

    Get complete configuration of a specific chart

  • list-dashboards

    List all dashboards in the project

  • create-dashboard

    Create a new dashboard (empty or with tiles)

  • run-dashboard-tiles

    Execute queries for dashboard tiles (supports bulk execution)

  • create-dashboard-tile

    Add a new tile (chart, markdown, or loom) to a dashboard

  • run-raw-query

    Execute an ad-hoc metric query against any explore

  • create-space

    Create a new space to organize charts and dashboards

Comparable tools

metabase-mcplooker-mcppowerbi-mcptableau-mcp

Installation

Installation

pip install lightdash-mcp

Claude Desktop Configuration

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "lightdash": {
      "command": "uvx",
      "args": ["lightdash-mcp"],
      "env": {
        "LIGHTDASH_TOKEN": "ldt_your_token_here",
        "LIGHTDASH_URL": "https://app.lightdash.cloud",
        "LIGHTDASH_PROJECT_UUID": "your-project-uuid"
      }
    }
  }
}

FAQ

How do I get my Lightdash Personal Access Token?
1. Log into your Lightdash instance 2. Go to Settings → Personal Access Tokens 3. Click 'Generate new token' 4. Copy the token (starts with 'ldt_')
Can I use this MCP server with self-hosted Lightdash?
Yes, just set your LIGHTDASH_URL environment variable to your self-hosted instance URL instead of the default Cloud URL.

Compare lightdash_mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.