lightdash-mcp-server logo

lightdash-mcp-server

by syucream

This server provides MCP-compatible access to Lightdash's API, allowing AI assistants to interact with your Lightdash data through a standardized interface. It's a Model Context Protocol (MCP) server that accesses Lightdash.

View on GitHub

Last updated: N/A

What is lightdash-mcp-server?

lightdash-mcp-server is a Model Context Protocol (MCP) server that allows AI assistants to access and interact with data stored in Lightdash through a standardized interface. It acts as a bridge between Lightdash's API and MCP-compatible AI applications.

How to use lightdash-mcp-server?

  1. Install the server using npm or Smithery. 2. Configure the server with your Lightdash API key and URL. 3. Start the server. 4. Configure your MCP configuration JSON to point to the server.

Key features of lightdash-mcp-server

  • MCP-compatible access to Lightdash

  • Provides tools to list projects, spaces, charts, and dashboards

  • Provides tools to get project details, custom metrics, and catalogs

  • Provides tools to get charts and dashboards as code

Use cases of lightdash-mcp-server

  • Enabling AI assistants to query and visualize data from Lightdash

  • Integrating Lightdash data into AI-powered workflows

  • Building custom AI applications that leverage Lightdash's data insights

  • Automating data analysis tasks using AI

FAQ from lightdash-mcp-server

What is MCP?

MCP stands for Model Context Protocol, a standardized interface for AI models to access external data and tools.

What is Lightdash?

Lightdash is a BI tool that connects to your data warehouse and allows you to create dashboards and charts.

How do I get a Lightdash API key?

You can generate a Personal Access Token (PAT) in your Lightdash settings.

What is the default API URL for Lightdash?

The default API URL is typically 'https://<your base url>'.

How can I contribute to this project?

Fork the repository, create a feature branch, run tests and linting, commit your changes, push to the branch, and create a pull request.