Redash MCP Server

Redash MCP Server

Enables interaction with Redash instances through a standardized interface, allowing users to execute SQL queries, manage data sources, and retrieve query results using natural language.

Category
访问服务器

README

Redash MCP Server

CI Docker Hub Docker Pulls License: MIT

A Model Context Protocol (MCP) server for Redash that provides query execution, data source management, and more through a standardized interface.

✨ Features

  • 🔍 Query Execution: Execute SQL queries and retrieve results
  • 📊 Data Source Management: List and inspect data sources
  • 🔐 Secure: API key-based authentication
  • 🐳 Docker Support: Easy deployment with Docker
  • Fully Tested: Comprehensive test coverage with TDD approach
  • 🚀 Modern Stack: Built with TypeScript, Vite, and latest tooling

📋 Requirements

  • Node.js: >= 22.0.0
  • pnpm: >= 9.0.0
  • Redash Instance: With API access
  • Docker (optional): For containerized deployment

🚀 Quick Start

Using npx (Recommended)

  1. Clone the repository:
git clone https://github.com/jasonsmithj/redash-mcp.git
cd redash-mcp
  1. Install dependencies:
pnpm install
  1. Build the project:
pnpm build
  1. Link globally:
pnpm link
  1. Configure your MCP client (Claude Desktop, Cursor, etc.):
{
  "mcpServers": {
    "redash": {
      "command": "npx",
      "args": ["redash-mcp"],
      "env": {
        "REDASH_API_KEY": "your_api_key_here",
        "REDASH_BASE_URL": "https://redash.example.com"
      }
    }
  }
}

Using Docker Hub (Recommended)

  1. Pull the latest image from Docker Hub:
docker pull jasonsmithj/redash-mcp:latest
  1. Run with Docker:
docker run -i --rm \
  -e REDASH_API_KEY=your_api_key \
  -e REDASH_BASE_URL=https://redash.example.com \
  jasonsmithj/redash-mcp:latest
  1. Or use Docker Compose:
# Create .env file
cp .env.example .env
# Edit .env with your credentials

# Start the service
docker compose up
  1. Configure your MCP client:
{
  "mcpServers": {
    "redash": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "REDASH_API_KEY",
        "-e",
        "REDASH_BASE_URL",
        "jasonsmithj/redash-mcp:latest"
      ],
      "env": {
        "REDASH_API_KEY": "your_api_key_here",
        "REDASH_BASE_URL": "https://redash.example.com"
      }
    }
  }
}

Building from Source

If you prefer to build from source:

docker build -t redash-mcp:local .

🔧 Configuration

Environment Variables

Variable Required Default Description
REDASH_API_KEY - Your Redash API key
REDASH_BASE_URL - Redash instance URL
REDASH_API_TIMEOUT 30000 API request timeout (milliseconds)

Getting Your Redash API Key

  1. Log in to your Redash instance
  2. Click on your profile icon → "Edit Profile"
  3. Copy your API key from the "API Key" section

🛠 Available Tools

1. list_data_sources

List all available data sources in Redash.

Parameters: None

Example:

List all data sources

2. get_data_source

Get details about a specific data source.

Parameters:

  • data_source_id (number): The ID of the data source

Example:

Get details for data source 1

3. execute_query_and_wait

Execute a SQL query and wait for the result.

Parameters:

  • query (string): The SQL query to execute
  • data_source_id (number): The ID of the data source
  • max_age (number, optional): Maximum age of cached results in seconds

Example:

Execute query "SELECT * FROM users LIMIT 10" on data source 1

4. list_queries

List all queries in Redash.

Parameters:

  • page (number, optional): Page number (default: 1)
  • page_size (number, optional): Results per page (default: 25)

Example:

List all queries

🧪 Development

Setup

# Install dependencies
pnpm install

# Run tests
pnpm test

# Run tests with UI
pnpm test:ui

# Run tests with coverage
pnpm test:coverage

# Type check
pnpm typecheck

# Lint
pnpm lint

# Format code
pnpm format

# Run all checks (CI equivalent)
pnpm ci

Testing with act

Test GitHub Actions locally using act:

# List available workflows
act -l

# Run CI workflow
act push

# Run specific job
act -j quality

Project Structure

redash-mcp/
├── src/
│   ├── index.ts              # MCP server entry point
│   ├── redash-client.ts      # Redash API client
│   ├── types.ts              # Type definitions
│   └── tools/                # MCP tools
│       ├── datasource.ts     # Data source tools
│       └── query.ts          # Query execution tools
├── tests/                    # Test files
├── scripts/                  # Build scripts
├── .github/
│   └── workflows/            # GitHub Actions CI/CD
├── Dockerfile                # Docker configuration
├── compose.yaml              # Docker Compose configuration
└── package.json

📦 Scripts

  • pnpm dev: Watch mode for development
  • pnpm build: Build for production
  • pnpm test: Run tests
  • pnpm test:coverage: Run tests with coverage report
  • pnpm lint: Lint code
  • pnpm format: Format code
  • pnpm ci: Run all quality checks

🏗 Tech Stack

  • Runtime: Node.js 22+ with ES Modules
  • Language: TypeScript 5.7+ (strict mode)
  • Build Tool: Vite 6.x
  • Package Manager: pnpm 9.x
  • Testing: Vitest 3.x with coverage
  • Linting: ESLint 9.x (Flat Config)
  • Formatting: Prettier 3.x
  • MCP SDK: @modelcontextprotocol/sdk 1.x

📦 Docker Images

Pre-built Docker images are available on Docker Hub:

  • Latest stable: jasonsmithj/redash-mcp:latest
  • Specific version: jasonsmithj/redash-mcp:v1.0.0
  • Major version: jasonsmithj/redash-mcp:1

Supported Platforms

Multi-architecture images are automatically built for both platforms:

  • linux/amd64 (x86_64) - Intel/AMD CPUs
    • Windows PCs
    • Intel-based Macs
    • Traditional Linux servers
  • linux/arm64 (ARM64) - ARM CPUs
    • Apple Silicon Macs (M1/M2/M3/M4)
    • ARM-based Linux servers
    • Raspberry Pi 4+ (64-bit)

Docker will automatically pull the correct image for your platform!

🚀 Releasing

To release a new version:

  1. Update version in package.json
  2. Commit changes: git commit -am "chore: bump version to vX.Y.Z"
  3. Create and push tag: git tag vX.Y.Z && git push origin vX.Y.Z
  4. GitHub Actions will automatically build and push to Docker Hub

🤝 Contributing

Contributions are welcome! Please follow these steps:

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes and add tests
  4. Run quality checks: pnpm ci
  5. Commit your changes: git commit -m 'Add amazing feature'
  6. Push to the branch: git push origin feature/amazing-feature
  7. Open a Pull Request

Development Guidelines

  • Follow TDD (Test-Driven Development) approach
  • Write tests before implementation
  • Maintain test coverage above 85%
  • Use conventional commits
  • Add JSDoc comments for public APIs
  • All code comments should be in English

Setting up GitHub Secrets for CD

To enable automated Docker Hub publishing, add the following secrets to your GitHub repository:

  1. Go to SettingsSecrets and variablesActions
  2. Add the following secrets:
    • DOCKER_USERNAME: Your Docker Hub username
    • DOCKER_PASSWORD: Your Docker Hub password or access token

For enhanced security, use a Docker Hub access token instead of your password:

  1. Log in to Docker Hub
  2. Go to Account SettingsSecurityNew Access Token
  3. Generate a token with "Read, Write, Delete" permissions
  4. Use this token as DOCKER_PASSWORD

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

📮 Support


Made with ❤️ by the Redash MCP community

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选