Lightdash
mcp server for lightdash
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
Maintainer
Works with
Installation
Manual Installation
npx lightdash-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Lightdash
Lightdash MCP is a Python-based Model Context Protocol server that connects AI assistants like Claude and Cursor to your Lightdash business intelligence instance, enabling them to discover data catalogs, run queries, create charts, and manage dashboards through natural language. The server exposes over 30 tools covering the full analytics workflow — from exploring table schemas and executing metric queries to building dashboard tiles and managing spaces. Teams running Lightdash on cloud or self-hosted infrastructure can use this server to let AI agents answer ad-hoc data questions, automate report creation, and update dashboards without requiring BI tool expertise.
Prerequisites
- Python 3.10 or higher
- A Lightdash instance (cloud at app.lightdash.cloud or self-hosted)
- A Lightdash Personal Access Token (generated from Lightdash Settings > Personal Access Tokens, starts with 'ldt_')
- The Lightdash project UUID (optional; falls back to the first available project if not set)
- An MCP client such as Claude Desktop or Claude Code
Install lightdash-mcp
Install the package from PyPI using pip, pipx, or use uvx to run it directly without permanent installation.
pip install lightdash-mcp
# or with pipx:
pipx install lightdash-mcp
# or run directly with uvx:
uvx lightdash-mcpGet your Lightdash Personal Access Token
Log into your Lightdash instance, navigate to Settings > Personal Access Tokens, and click 'Generate new token'. Copy the token — it starts with 'ldt_'.
Find your Lightdash project UUID
In Lightdash, go to your project settings or look at the URL when viewing a project — the UUID is the alphanumeric string in the path (e.g., /projects/3fc2835f-...). This is optional; the server falls back to the first available project.
Configure your MCP client
Add lightdash-mcp to your claude_desktop_config.json or equivalent config file. The LIGHTDASH_TOKEN and LIGHTDASH_URL variables are required.
{
"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"
}
}
}
}Verify the connection
Restart your MCP client and ask it to list Lightdash projects or explores. If connected correctly, it will return your project and table names.
Lightdash Examples
Client configuration
Claude Desktop configuration using uvx to run lightdash-mcp with your Lightdash cloud credentials.
{
"mcpServers": {
"lightdash": {
"command": "uvx",
"args": ["lightdash-mcp"],
"env": {
"LIGHTDASH_TOKEN": "ldt_your_token_here",
"LIGHTDASH_URL": "https://app.lightdash.cloud",
"LIGHTDASH_PROJECT_UUID": "3fc2835f-0000-0000-0000-000000000000"
}
}
}
}Prompts to try
Example prompts for exploring data, querying metrics, and building dashboards with Lightdash.
- "List all available explores and tables in my Lightdash project"
- "Show me the schema for the 'orders' explore including all dimensions and metrics"
- "Run a query on the orders table showing total revenue by month for the last 6 months"
- "Create a new chart showing daily active users over the past 30 days and add it to the 'Growth' dashboard"
- "List all dashboards in the project and show me the tiles in the 'Executive Summary' dashboard"Troubleshooting Lightdash
Authentication error: 401 Unauthorized
Verify that LIGHTDASH_TOKEN is set correctly and has not expired. Personal Access Tokens can expire — regenerate one in Lightdash Settings > Personal Access Tokens. Also ensure LIGHTDASH_URL matches your actual instance URL exactly (no trailing slash).
Tools return empty results or 'project not found'
If LIGHTDASH_PROJECT_UUID is not set, the server uses the first available project. To target a specific project, find its UUID in the Lightdash URL or project settings and set LIGHTDASH_PROJECT_UUID in the env block.
Connection error when behind Google Cloud IAP
Install the IAP extra: 'pip install lightdash-mcp[iap]'. Then set IAP_ENABLED=true in your environment. If using user credentials (ADC), also set IAP_SA to your service account email. The runtime service account needs roles/iap.httpsResourceAccessor on the Cloud Run service.
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?
Follow the installation instructions on the Lightdash GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
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.
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
★ 14.0kOpenMetadata 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
★ 10.9kAn 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
★ 4.1kEnables 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
★ 997Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Weather MCP Server
★ 907Weather 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.
Set Up Lightdash in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
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.