Using AI with Lightdash

Lightdash offers multiple AI-powered capabilities to help you explore data, build your semantic layer, and integrate with external tools.

Lightdash provides several ways to leverage AI across your analytics workflow. Each capability serves a different use case—from answering business questions to building your semantic layer to integrating with your own AI tools.

AI capabilities at a glance

Capability	Use case	Requirements
Lightdash AI agents	Answer questions and create charts using your semantic layer	Cloud Pro or Enterprise add-on
Lightdash Data MCP	Query your semantic layer from external LLMs	All Lightdash Cloud and Enterprise users
Lightdash Docs MCP	Give your LLM context about Lightdash features	Free for everyone
Agent skills for your CLI	Build and maintain your semantic layer with external AI coding agents	Free for everyone

Lightdash AI agents

Available as an add-on for Cloud Pro and Enterprise plans. View pricing

AI agents let your team ask questions in natural language and get instant answers. They use your saved dashboards and the metrics defined in your semantic layer, so business users can find insights without writing code or learning complex tools.

Best for: Business users who want to explore data and create visualizations without technical knowledge.

Key features:

• Natural language queries with automatic visualizations
• Slack integration for team collaboration
• Memory and learning from corrections
• Fine-grained access control
• Evaluations to validate agent accuracy

AI agents documentation

Learn how to set up and use AI agents

Lightdash Data MCP

Available to all Lightdash Cloud and Enterprise users.

The Model Context Protocol (MCP) lets you connect external AI assistants like Claude or ChatGPT directly to your Lightdash data. Use your preferred LLM to explore data models, search for metrics, and get data-driven insights—all while respecting your existing access controls.

Best for: Teams who want to use their own AI tools (Claude, ChatGPT, custom agents) to query Lightdash data outside the Lightdash UI.

Key features:

• Connect Claude, ChatGPT, or custom agents to your Lightdash instance
• Browse and query your data models
• Run arbitrary SQL queries against your data warehouse for ad-hoc analysis
• OAuth authentication with existing permissions

Lightdash Data MCP documentation

Set up MCP with your AI assistant

Lightdash Docs MCP

Free for everyone—open source users and all cloud tiers.

The Docs MCP endpoint gives AI coding agents access to the complete Lightdash documentation. This helps your LLM understand Lightdash concepts, generate accurate YAML configurations, and troubleshoot issues using official documentation.

Best for: Developers who want their AI coding tools to have context about Lightdash when working on configurations.

Key features:

• Full access to Lightdash documentation
• No authentication required
• Works with Cursor, Claude Code, Windsurf, and other MCP-compatible tools

Setup

Add the Docs MCP endpoint to your AI coding tool:

Cursor

Add to your .cursor/mcp.json:

{
  "mcpServers": {
    "lightdash-docs": {
      "url": "https://docs.lightdash.com/mcp"
    }
  }
}

Claude Code

Run the following command:

claude mcp add lightdash-docs https://docs.lightdash.com/mcp -t http

Windsurf

Add to your ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "lightdash-docs": {
      "serverUrl": "https://docs.lightdash.com/mcp"
    }
  }
}

Agent skills

Free for everyone—open source users and all cloud tiers.

Agent skills teach AI coding agents like Cursor, Claude Code, and Codex about Lightdash’s YAML configuration, metrics, dimensions, and best practices. Install skills to help your AI assistant generate correct configurations and follow Lightdash conventions.

Best for: Developers building and maintaining their semantic layer who want AI assistance with YAML configurations.

Key features:

• Generate correct YAML for metrics and dimensions
• Follow Lightdash naming conventions automatically
• Understand table relationships and joins
• Stay current with latest Lightdash features

Quick start

# Install for Claude (default)
lightdash install-skills

# Install for Cursor
lightdash install-skills --agent cursor

# Install for Codex
lightdash install-skills --agent codex

Agent skills documentation

Learn more about installing and using agent skills

Choosing the right AI capability

Not sure which surface to point a user at? See Choosing the right AI workflow in Lightdash for a decision tree, a comparison table, and guidance on when to use agents, MCP, YAML, or dashboards as code.

If you want to…	Use
Let business users ask questions in natural language	Lightdash AI agents
Query Lightdash data from Claude, ChatGPT, or custom agents	Lightdash Data MCP
Help your coding AI understand Lightdash documentation	Lightdash Docs MCP
Get AI help writing YAML configurations	Agent skills for your CLI
Decide between agents, MCP, YAML, and dashboards as code	Choosing the right AI workflow