Lightdash MCP Server

A Model Context Protocol (MCP) server for interacting with Lightdash, enabling LLMs to discover data, create charts, and manage dashboards programmatically.

Features

This MCP server provides a comprehensive set of tools for the full data analytics workflow:

• Discovery: Explore data catalogs, find tables/explores, and understand schemas
• Querying: Execute queries with full filter, metric, and aggregation support
• Chart Management: Create, read, update, and delete charts with complex visualizations
• Dashboard Management: Build and manage dashboards with tiles, filters, and layouts
• Resource Organization: Create and manage spaces for content organization

Installation

Prerequisites

• Python 3.10+
• A Lightdash instance (Cloud or self-hosted)
• Lightdash Personal Access Token (obtain from your Lightdash profile settings)

Quick Start with uvx (Recommended)

The easiest way to use this MCP server is with uvx, which will automatically download and run it:

uvx --from git+https://github.com/<owner>/lightdash-mcp lightdash-mcp

Quick Start with pipx

Alternatively, you can use pipx:

pipx run --spec git+https://github.com/<owner>/lightdash-mcp lightdash-mcp

Install from Source

git clone <repository-url>
cd lightdash_mcp
pip install .

Configuration

Environment Variables

The server requires the following environment variables:

Variable	Required	Description	Example
LIGHTDASH_TOKEN	✅	Your Lightdash Personal Access Token	ldt_abc123...
LIGHTDASH_URL	✅	Base URL of your Lightdash API	https://app.lightdash.cloud/api/v1
CF_ACCESS_CLIENT_ID	❌	Cloudflare Access Client ID (if behind CF Access)	-
CF_ACCESS_CLIENT_SECRET	❌	Cloudflare Access Client Secret (if behind CF Access)	-

Getting Your Lightdash Token

1. Log into your Lightdash instance
2. Go to Settings → Personal Access Tokens
3. Click Generate new token
4. Copy the token (starts with ldt_)

Usage with Claude Desktop (uvx)

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "lightdash": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/<owner>/lightdash_mcp",
        "lightdash-mcp"
      ],
      "env": {
        "LIGHTDASH_TOKEN": "ldt_your_token_here",
        "LIGHTDASH_URL": "https://app.lightdash.cloud/api/v1"
      }
    }
  }
}

Usage with Claude Desktop (pipx)

If you prefer pipx, use this configuration:

{
  "mcpServers": {
    "lightdash": {
      "command": "pipx",
      "args": [
        "run",
        "--spec",
        "git+https://github.com/<owner>/lightdash_mcp",
        "lightdash-mcp"
      ],
      "env": {
        "LIGHTDASH_TOKEN": "ldt_your_token_here",
        "LIGHTDASH_URL": "https://app.lightdash.cloud/api/v1"
      }
    }
  }
}

Note: Replace <owner> with the GitHub username or organization hosting the repository.

Usage with Other MCP Clients

Export the environment variables before running:

export LIGHTDASH_TOKEN="ldt_your_token_here"
export LIGHTDASH_URL="https://app.lightdash.cloud/api/v1"
lightdash-mcp

Available Tools

📊 Discovery & Metadata

Tool	Description
list-projects	List all available Lightdash projects
get-project	Get detailed information about a specific project
list-explores	List all available explores/tables in a project
get-explore-schema	Get detailed schema for a specific explore (dimensions, metrics, joins)
list-spaces	List all spaces (folders) in the project
get-custom-metrics	Get custom metrics defined in the project

📈 Chart Management

Tool	Description
list-charts	List all saved charts, optionally filtered by name
search-charts	Search for charts by name or description
get-chart-details	Get complete configuration of a specific chart
create-chart	Create a new saved chart with metric query and visualization config
update-chart	Update an existing chart's configuration (name, description, queries, visualization)
run-chart-query	Execute a chart's query and retrieve the data
delete-chart	Delete a saved chart

📋 Dashboard Management

Tool	Description
list-dashboards	List all dashboards in the project
create-dashboard	Create a new dashboard (empty or with tiles)
duplicate-dashboard	Clone an existing dashboard with a new name
get-dashboard-tiles	Get all tiles from a dashboard with optional full config
get-dashboard-tile-chart-config	Get complete chart configuration for a specific dashboard tile
get-dashboard-code	Get the complete dashboard configuration as code
create-dashboard-tile	Add a new tile (chart, markdown, or loom) to a dashboard
update-dashboard-tile	Update tile properties (position, size, content)
rename-dashboard-tile	Rename a dashboard tile
delete-dashboard-tile	Remove a tile from a dashboard
update-dashboard-filters	Update dashboard-level filters
run-dashboard-tiles	Execute one, multiple, or all tiles on a dashboard concurrently

🔍 Query Execution

Tool	Description
run-chart-query	Execute a saved chart's query and return data
run-dashboard-tiles	Run queries for dashboard tiles (supports bulk execution)
run-raw-query	Execute an ad-hoc metric query against any explore

🗂️ Resource Management

Tool	Description
create-space	Create a new space to organize charts and dashboards
delete-space	Delete an empty space

Project Structure

.
├── pyproject.toml              # Package configuration
├── lightdash_mcp/              # Main package
│   ├── __init__.py             # Package init
│   ├── server.py               # MCP server entry point
│   ├── lightdash_client.py     # Lightdash API client
│   └── tools/                  # Tool implementations
│       ├── __init__.py         # Auto-discovery and tool registry
│       ├── base_tool.py        # Base tool interface
│       └── *.py                # Individual tool implementations
├── README.md
└── LICENSE

Development

Adding a New Tool

The server automatically discovers and registers tools from the tools/ directory. To add a new tool:

1. Create a new file in lightdash_mcp/tools/ (e.g., my_new_tool.py)

2. Define the tool:

   from pydantic import BaseModel, Field
   from .base_tool import ToolDefinition
   from .. import lightdash_client as client
   
   class MyToolInput(BaseModel):
       param1: str = Field(..., description="Description of param1")
   
   TOOL_DEFINITION = ToolDefinition(
       name="my-new-tool",
       description="Description of what this tool does",
       input_schema=MyToolInput
   )
   
   def run(param1: str) -> dict:
       """Execute the tool logic"""
       result = client.get(f"/some/endpoint/{param1}")
       return result
   

3. Restart the server - the tool will be automatically registered

Tool Registry

Tools are automatically discovered via tools/__init__.py, which:

• Scans the tools/ directory for Python modules
• Imports each module (excluding utility modules)
• Registers tools by their TOOL_DEFINITION.name

Testing

You can test individual tools by importing them:

from tools import tool_registry

# List all registered tools
print(tool_registry.keys())

# Test a specific tool
result = tool_registry['list-projects'].run()
print(result)

Troubleshooting

Authentication Errors

If you see 401 Unauthorized errors:

• Verify your LIGHTDASH_TOKEN is correct and starts with ldt_
• Check that the token hasn't expired
• Ensure you have the necessary permissions in Lightdash

Connection Errors

If you see connection errors:

• Verify LIGHTDASH_URL is correct (should end with /api/v1)
• For Lightdash Cloud: use https://app.lightdash.cloud/api/v1
• For self-hosted: use https://your-domain.com/api/v1
• If behind Cloudflare Access, ensure CF_ACCESS_CLIENT_ID and CF_ACCESS_CLIENT_SECRET are set

Tool Not Found

If a tool isn't showing up:

• Check that the file is in the tools/ directory
• Ensure the file has a TOOL_DEFINITION variable
• Verify the file isn't in the exclusion list in tools/__init__.py
• Restart the MCP server

Contributing

Contributions are welcome! Please:

1. Fork the repository
2. Create a feature branch
3. Add your changes with appropriate tests
4. Submit a pull request

License

[Add your license here]

Support

For issues and questions:

• Lightdash Documentation
• Lightdash Community Slack
• MCP Documentation