Skip to main content

Cloud Pro

Cloud Enterprise

The Model Context Protocol (MCP) enables AI assistants (e.g. ChatGPT, Claude) and custom agents to directly interact with your Lightdash data. This integration allows MCP clients to explore your data models, search for metrics and dimensions, and provide data-driven insights - all through natural conversation. You can use MCP with existing AI assistants or integrate it into your own custom agents and automated workflows. MCP uses secure OAuth authentication and respects all your existing access controls, ensuring data remains protected. With MCP, your AI assistant becomes a data analyst that can:
  • Browse and understand your data models
  • Find relevant metrics and dimensions
  • Switch between different projects seamlessly
  • Respect your data governance and access controls
MCP respects all your existing Lightdash permissions and user attributes. MCP clients can only access the data that your user account has permission to view.

​
Get started

Setting up MCP is quick and straightforward. You can connect your AI assistant to your Lightdash instance in just a few minutes.

​
Prerequisites

  • A Lightdash Cloud Pro or Enterprise account with MCP enabled
  • An MCP-compatible AI assistant (e.g., Claude.ai, Claude Desktop, ChatGPT)

​
Installation

​
Claude.ai (Web & Desktop Apps)

Set up MCP in the Claude.ai web app, and it will automatically sync to your Claude Desktop app after restart.
  1. Access Settings in Claude.ai Navigate to your profile menu (bottom-left corner) and select Settings.
    Navigate to profile menu in bottom-left corner and click Settings
  2. Add Custom Connector In the Settings menu, select “Connectors” from the sidebar, then click “Add custom connector”.
    Select Connectors from the sidebar menu, then click Add custom connector button
  3. Configure Connection Fill in the connection details with your Lightdash instance information.
    Enter Lightdash as the name and your instance MCP URL in the configuration form
    • Name: Lightdash (or any name you prefer)
    • URL: https://<your_instance_name>.lightdash.cloud/api/v1/mcp
  4. Connect and Authenticate Click the “Connect” button to initiate the authentication process.
    Click the Connect button to start OAuth authentication with Lightdash
  5. Complete OAuth Flow Log in to your Lightdash account and approve the connection when prompted.
    Login to Lightdash with your credentials and approve the OAuth connection request
  6. Configure Permissions (Optional) Optionally configure which MCP tools Claude can access and set any additional permissions.
    Optional: Configure MCP tool access and permissions for your Claude assistant

​
ChatGPT (Web App)

ChatGPT support for MCP is coming soon! Stay tuned for updates.