Lightdash
MCP-compatible server that enables AI assistants to interact with Lightdash analytics data, providing tools to list and retrieve projects, spaces, charts, dashboards, and metrics through a standardized interface.
What is Lightdash?
Lightdash is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp-compatible server that enables ai assistants to interact with lightdash analytics data, providing tools to list and retrieve projects, spaces, charts, dashboards, and metrics through a standardize...
MCP-compatible server that enables AI assistants to interact with Lightdash analytics data, providing tools to list and retrieve projects, spaces, charts, dashboards, and metrics through a standardized interface.
This server falls under the Analytics category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP-compatible server that enables AI assistants to interact
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx lightdash-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Lightdash
Lightdash MCP Server connects AI assistants to a Lightdash analytics instance, exposing projects, spaces, charts, dashboards, and the metrics catalog through a standardized MCP interface. It enables natural language querying of business intelligence assets — so instead of navigating the Lightdash UI, you can ask Claude to list all dashboards in a project, retrieve a chart's data, or export assets as code. Both stdio and HTTP transports are supported, making it flexible for local and server deployments.
Prerequisites
- Node.js 16 or later with npm and npx available
- A running Lightdash instance (cloud or self-hosted)
- A Lightdash Personal Access Token (generated in your Lightdash profile settings)
- The base URL of your Lightdash instance
- An MCP client such as Claude Desktop
Obtain a Lightdash Personal Access Token
Log in to your Lightdash instance, navigate to your profile settings, and generate a Personal Access Token. Copy the token value — you will need it as the LIGHTDASH_API_KEY environment variable.
Install the MCP server package
Install lightdash-mcp-server globally via npm, or use npx to run it directly without a permanent installation.
npm install -g lightdash-mcp-serverSet the required environment variables
The server requires two environment variables: LIGHTDASH_API_KEY (your Personal Access Token) and LIGHTDASH_API_URL (the base URL of your Lightdash instance including protocol and host).
export LIGHTDASH_API_KEY="your-personal-access-token"
export LIGHTDASH_API_URL="https://your-lightdash-instance.example.com"Configure your MCP client
Add the server to your MCP client configuration. The environment variables must be passed through the config so the server can authenticate with Lightdash.
{
"mcpServers": {
"lightdash": {
"command": "npx",
"args": ["lightdash-mcp-server"],
"env": {
"LIGHTDASH_API_KEY": "your-personal-access-token",
"LIGHTDASH_API_URL": "https://your-lightdash-instance.example.com"
}
}
}
}Verify available tools
Restart your MCP client and confirm the server is connected. The server exposes ten tools: list_projects, get_project, list_spaces, list_charts, list_dashboards, get_custom_metrics, get_catalog, get_metrics_catalog, get_charts_as_code, and get_dashboards_as_code.
Optional: run in HTTP mode
For server deployments where you want to share a single Lightdash MCP endpoint across multiple clients, start the server in HTTP mode and point clients at the HTTP URL.
npx lightdash-mcp-server -port 8080
# Clients connect to: http://localhost:8080/mcpLightdash Examples
Client configuration
Stdio configuration for Claude Desktop with authentication credentials passed as environment variables.
{
"mcpServers": {
"lightdash": {
"command": "npx",
"args": ["lightdash-mcp-server"],
"env": {
"LIGHTDASH_API_KEY": "your-personal-access-token",
"LIGHTDASH_API_URL": "https://your-lightdash-instance.example.com"
}
}
}
}Prompts to try
Use these prompts with Claude once Lightdash MCP Server is connected to explore your analytics assets.
- "List all projects in my Lightdash instance"
- "Show me all dashboards in the Marketing space"
- "Get the metrics catalog for project abc123 and summarize the available KPIs"
- "Export the Revenue dashboard as code so I can version-control it"
- "What charts are available in the Sales project?"Troubleshooting Lightdash
Authentication errors or 401 responses from Lightdash
Verify that LIGHTDASH_API_KEY contains a valid Personal Access Token (not your login password) and that the token has not been revoked. Regenerate a new token from your Lightdash profile settings if needed.
LIGHTDASH_API_URL connection refused or timeout
Confirm the URL includes the correct protocol (https://) and no trailing slash. For self-hosted instances, ensure the Lightdash server is running and accessible from the machine where the MCP server runs.
HTTP mode clients cannot connect
When using HTTP mode (-port 8080), the environment variables must be set in the shell where npx lightdash-mcp-server runs, not in the client config. Start the server process manually with the env vars exported before launching the HTTP listener.
Frequently Asked Questions about Lightdash
What is Lightdash?
Lightdash is a Model Context Protocol (MCP) server that mcp-compatible server that enables ai assistants to interact with lightdash analytics data, providing tools to list and retrieve projects, spaces, charts, dashboards, and metrics through a standardized interface. 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 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.