Interact with [Lightdash](https://www.lightdash.com/), a BI tool.
Documentation
lightdash-mcp-server
Features
Available tools:
list_projects
get_project
list_spaces
list_charts
list_dashboards
get_custom_metrics
get_catalog
get_metrics_catalog
get_charts_as_code
get_dashboards_as_code
Quick Start# Installation\n\n#### Installing via Smithery
To install Lightdash MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install lightdash-mcp-server --client claude
```\n\n#### Manual Installation
```bash
npm install lightdash-mcp-server
```\n\n### Configuration
- `LIGHTDASH_API_KEY`: Your Lightdash PAT
- `LIGHTDASH_API_URL`: The API base URL\n\n### Usage
The lightdash-mcp-server supports two transport modes: **Stdio** (default) and **HTTP**.\n\n#### Stdio Transport (Default)
1. Start the MCP server:
```bash
npx lightdash-mcp-server
Edit your MCP configuration json:
...
"lightdash": {
"command": "npx",
"args": [ "-y", "lightdash-mcp-server" ],
"env": {
"LIGHTDASH_API_KEY": "",
"LIGHTDASH_API_URL": "https://"
}
},
...
```\n\n#### HTTP Transport (Streamable HTTP)
1. Start the MCP server in HTTP mode:
```bash
npx lightdash-mcp-server -port 8080
Configure your MCP client to connect via HTTP:
...
"lightdash": {
"url": "http://localhost:8080/mcp"
},
...
```\n\n## Development# Available Scripts
- `npm run dev`
- `npm run dev:http`
- `npm run build`
- `npm run start`
- `npm run lint`
- `npm run fix`
- `npm run examples`\n\n### Contributing
1. Fork the repository
2. Create your feature branch
3. Run tests and linting: `npm run lint`
4. Commit your changes
5. Push to the branch
6. Create a Pull Request