MCPgee
MCPgee
MCPgeeMCPgee

Lightdash

v1.0.0•Analytics•stable

mcp server for lightdash

analyticsbusiness-intelligenceclaudedata-visualizationlightdash
Share:
19
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Lightdash?

Lightdash is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for lightdash

mcp server for lightdash

This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • mcp server for lightdash

Use Cases

Lightdash analytics platform integration
Data visualization and BI
poddubnyoleg

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 17, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

NPM

npx -y lightdash

Manual Installation

npx -y lightdash

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Lightdash

The Lightdash MCP Server bridges your AI assistant with Lightdash, the open-source BI and analytics platform, exposing over 30 tools for querying data, managing charts and dashboards, and exploring your data catalog through natural language. It connects via Lightdash's Personal Access Token and supports both cloud and self-hosted Lightdash instances, including deployments behind Google Cloud IAP or Cloudflare Access. Data teams use it to run ad-hoc queries, build dashboards, and explore explores without leaving their AI assistant.

Prerequisites

  • Python 3.9 or later (for pip/uvx installation)
  • A Lightdash account with a Personal Access Token (format: ldt_...) from Lightdash Settings
  • The base URL of your Lightdash instance (e.g. https://app.lightdash.cloud)
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Install the Lightdash MCP server

Install via pip. For Google Cloud IAP support, install the optional extra.

pip install lightdash-mcp
# or with IAP support:
pip install lightdash-mcp[iap]
2

Obtain your Lightdash Personal Access Token

Log into Lightdash, go to Settings > Personal Access Tokens, and create a new token. Copy the token value (starts with ldt_).

3

Configure your MCP client

Add the lightdash-mcp server to your claude_desktop_config.json, providing the required LIGHTDASH_TOKEN and LIGHTDASH_URL environment variables.

4

Add the server entry to claude_desktop_config.json

Use uvx for zero-install-overhead invocation, passing env vars for authentication.

{
  "mcpServers": {
    "lightdash": {
      "command": "uvx",
      "args": ["lightdash-mcp"],
      "env": {
        "LIGHTDASH_TOKEN": "ldt_your_token_here",
        "LIGHTDASH_URL": "https://app.lightdash.cloud"
      }
    }
  }
}
5

Restart Claude Desktop

Restart the client to load the new server. The server will authenticate with Lightdash on startup.

6

Optionally set the default project

If you have multiple projects, set LIGHTDASH_PROJECT_UUID to avoid specifying it on every query.

LIGHTDASH_PROJECT_UUID=xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx

Lightdash Examples

Client configuration

Claude Desktop configuration for the Lightdash MCP server with required authentication variables.

{
  "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"
      }
    }
  }
}

Prompts to try

Example prompts you can use once the Lightdash server is connected.

- "List all available explores in my Lightdash project."
- "Run a query on the orders explore showing total revenue by month."
- "Create a new dashboard called 'Weekly Sales KPIs'."
- "Show me the schema for the users explore."
- "Create a saved chart for daily active users over the last 30 days."

Troubleshooting Lightdash

Authentication error: invalid token or 401 Unauthorized

Verify that LIGHTDASH_TOKEN starts with 'ldt_' and was copied without extra whitespace. Generate a fresh token in Lightdash Settings > Personal Access Tokens if necessary.

Connection refused or unreachable for self-hosted Lightdash

Ensure LIGHTDASH_URL points to your instance without a trailing slash (e.g. https://lightdash.company.com). For IAP-protected deployments, set IAP_ENABLED=true and provide CF_ACCESS_CLIENT_ID / CF_ACCESS_CLIENT_SECRET.

uvx command not found

Install uv with 'pip install uv' or 'curl -LsSf https://astral.sh/uv/install.sh | sh', then retry. Alternatively, replace 'uvx' with 'python -m lightdash_mcp' in the config.

Frequently Asked Questions about Lightdash

What is Lightdash?

Lightdash is a Model Context Protocol (MCP) server that mcp server for lightdash It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Lightdash?

Install via npm with the command: npx -y lightdash. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Lightdash?

Lightdash works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Lightdash free to use?

Yes, Lightdash is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Lightdash Alternatives — Similar Analytics Servers

Looking for alternatives to Lightdash? Here are other popular analytics servers you can use with Claude, Cursor, and VS Code.

OpenMetadata

★ 14.0k

OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance powered by a central metadata repository, in-depth column level lineage, and seamless team collaboration.

Superset

★ 10.9k

An MCP server that provides AI assistants with full access to Apache Superset instances, enabling interaction with dashboards, charts, datasets, databases, and SQL execution capabilities.

Horizon

★ 4.4k

📡 Your own AI-powered news radar. Generates daily briefings in English & Chinese. | 用 AI 构建你专属的新闻雷达

MCP Server Chart

★ 4.1k

Enables generation of 25+ types of charts and data visualizations using AntV, including bar charts, line charts, maps, mind maps, and specialized diagrams like fishbone and sankey charts. Supports both statistical charts and geographic visualizations

Muapi CLI

★ 997

Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.

Weather MCP Server

★ 907

Weather Data Fetcher MCP server built with Node.js, MCP SDK, and Zod. Provides weather details like temperature and forecast for cities such as Noida and Delhi via a registered tool. Simplifies API integration, enabling structured responses for clien

Browse More Analytics MCP Servers

Explore all analytics servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

AnalyticsBrowse All Servers

Quick Config Preview

{ "mcpServers": { "lightdash": { "command": "npx", "args": ["-y", "lightdash"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Lightdash?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides