MCP ExplorerExplorer

Redash Mcp

@suthioon 9 months ago
21 MIT
FreeCommunity
AI Systems
Redash MCP server integrates Redash with AI assistants, enabling query management and execution.

Overview

What is Redash Mcp

Redash MCP is a Model Context Protocol server designed to integrate Redash with AI assistants like Claude, enabling seamless interaction with data visualizations and queries.

Use cases

Use cases include automating data retrieval from Redash for reporting, integrating data queries into AI-driven applications, and enhancing user interaction with data through AI assistants.

How to use

To use Redash MCP, clone the repository, install dependencies, configure your Redash instance in a .env file, build the project, and start the server. Additionally, configure it in the Claude for Desktop configuration file for integration.

Key features

Key features include connecting to Redash instances via API, listing available queries and dashboards, executing queries, managing queries (create, update, archive), listing data sources, and retrieving dashboard details and visualizations.

Where to use

Redash MCP can be used in data analysis, business intelligence, and any field that requires integration of data visualization tools with AI assistants for enhanced data accessibility and insights.

Content

Redash MCP Server

Model Context Protocol (MCP) server for integrating Redash with AI assistants like Claude.

Redash Server MCP server

Features

  • Connect to Redash instances via the Redash API
  • List available queries and dashboards as resources
  • Execute queries and retrieve results
  • Create and manage queries (create, update, archive)
  • List data sources for query creation
  • Get dashboard details and visualizations

Prerequisites

  • Node.js (v18 or later)
  • npm or yarn
  • Access to a Redash instance
  • Redash API key

Environment Variables

The server requires the following environment variables:

Optional variables:

  • REDASH_TIMEOUT: Timeout for API requests in milliseconds (default: 30000)
  • REDASH_MAX_RESULTS: Maximum number of results to return (default: 1000)

Installation

  1. Clone this repository:

    git clone https://github.com/suthio/redash-mcp.git
    cd redash-mcp
    
  2. Install dependencies:

    npm install
    
  3. Create a .env file with your Redash configuration:

    REDASH_URL=https://your-redash-instance.com
    REDASH_API_KEY=your_api_key
    
  4. Build the project:

    npm run build
    
  5. Start the server:

    npm start
    

Usage with Claude for Desktop

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"
      }
    }
  }
}

Available Tools

Query Management

  • list-queries: List all available queries in Redash
  • get-query: Get details of a specific query
  • create-query: Create a new query in Redash
  • update-query: Update an existing query in Redash
  • archive-query: Archive (soft-delete) a query
  • list-data-sources: List all available data sources

Query Execution

  • execute-query: Execute a query and return results

Dashboard Management

  • list-dashboards: List all available dashboards
  • get-dashboard: Get dashboard details and visualizations
  • get-visualization: Get details of a specific visualization

Development

Run in development mode:

npm run dev

Version History

  • v1.1.0: Added query management functionality (create, update, archive)
  • v1.0.0: Initial release

License

MIT

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers