Model Context Protocol (MCP) server for integrating Redash with AI assistants like Claude.
The server requires the following environment variables:
REDASH_URL
: Your Redash instance URL (e.g., https://redash.example.com)REDASH_API_KEY
: Your Redash API keyOptional variables:
REDASH_TIMEOUT
: Timeout for API requests in milliseconds (default: 30000)REDASH_MAX_RESULTS
: Maximum number of results to return (default: 1000)Clone this repository:
git clone https://github.com/suthio/redash-mcp.git
cd redash-mcp
Install dependencies:
npm install
Create a .env
file with your Redash configuration:
REDASH_URL=https://your-redash-instance.com
REDASH_API_KEY=your_api_key
Build the project:
npm run build
Start the server:
npm start
To use this MCP server with Claude for Desktop, configure it in your Claude for Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the following configuration (edit paths as needed):
{
"mcpServers": {
"redash": {
"command": "npx",
"args": [
"-y",
"@suthio/redash-mcp"
],
"env": {
"REDASH_API_KEY": "your-api-key",
"REDASH_URL": "https://your-redash-instance.com"
}
}
}
}
list-queries
: List all available queries in Redashget-query
: Get details of a specific querycreate-query
: Create a new query in Redashupdate-query
: Update an existing query in Redasharchive-query
: Archive (soft-delete) a querylist-data-sources
: List all available data sourcesexecute-query
: Execute a query and return resultsexecute-adhoc-query
: Execute an ad-hoc query without saving it to Redashlist-dashboards
: List all available dashboardsget-dashboard
: Get dashboard details and visualizationsget-visualization
: Get details of a specific visualizationcreate-visualization
: Create a new visualization for a queryupdate-visualization
: Update an existing visualizationdelete-visualization
: Delete a visualizationRun in development mode:
npm run dev
MIT
An MCP server for chatting with your Lighthouse portfolio
An MCP server that provides LLMs with efficient access to package documentation across multiple programming languages
Example of an MCP server with custom tools that can be called directly from cursor