Want a ready-to-use AI experience for DataWorks without manual MCP setup?

DataWorks Agent is Alibaba Cloud's built-in intelligent assistant for data development and operations. It connects to your DataWorks workspace out of the box, so you can use natural language to explore metadata, develop nodes, troubleshoot tasks, and manage resources—no local MCP server configuration required.

👉 Get started: https://dataworks.data.alibabacloud.com/product/agent?source=github

A Model Context Protocol (MCP) server that provides tools for AI, allowing it to interact with the DataWorks Open API through a standardized interface. This implementation is based on the Aliyun Open API and enables AI agents to perform cloud resources operations seamlessly.

If you prefer embedding DataWorks capabilities into your own AI workflow or IDE, follow the installation guide below.

This MCP server:

• Interact with DataWorks Open API
• Manage DataWorks resources

The server implements the Model Context Protocol specification to standardize cloud resource interactions for AI agents.

• Node.js (v16 or higher)
• pnpm (recommended), npm, or yarn
• DataWorks Open API with access key and secret key

# Install globally
npm install -g alibabacloud-dataworks-mcp-server

# Or install locally in your project
npm install alibabacloud-dataworks-mcp-server

1. Clone this repository:

git clone https://github.com/aliyun/alibabacloud-dataworks-mcp-server
cd alibabacloud-dataworks-mcp-server

2. Install dependencies (pnpm is recommended, npm is supported):

pnpm install

3. Build the project:

pnpm run build

4. Development the project (by @modelcontextprotocol/inspector):

pnpm run dev

open http://localhost:5173

If you installed via npm (Option 1):

{
  "mcpServers": {
    "alibabacloud-dataworks-mcp-server": {
      "command": "npx",
      "args": ["alibabacloud-dataworks-mcp-server"],
      "env": {
        "REGION": "your_dataworks_open_api_region_id_here",
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "your_alibaba_cloud_access_key_id",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "your_alibaba_cloud_access_key_secret",
        "TOOL_CATEGORIES": "optional_your_tool_categories_here_ex_UTILS",
        "TOOL_NAMES": "optional_your_tool_names_here_ex_ListProjects"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

If you built from source (Option 2):

{
  "mcpServers": {
    "alibabacloud-dataworks-mcp-server": {
      "command": "node",
      "args": ["/path/to/alibabacloud-dataworks-mcp-server/build/index.js"],
      "env": {
        "REGION": "your_dataworks_open_api_region_id_here",
        "ALIBABA_CLOUD_ACCESS_KEY_ID": "your_alibaba_cloud_access_key_id",
        "ALIBABA_CLOUD_ACCESS_KEY_SECRET": "your_alibaba_cloud_access_key_secret",
        "TOOL_CATEGORIES": "optional_your_tool_categories_here_ex_SERVER_IDE_DEFAULT",
        "TOOL_NAMES": "optional_your_tool_names_here_ex_ListProjects"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

init variables in your environment:

# DataWorks Configuration
REGION=your_dataworks_open_api_region_id_here
ALIBABA_CLOUD_ACCESS_KEY_ID=your_alibaba_cloud_access_key_id
ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_alibaba_cloud_access_key_secret
TOOL_CATEGORIES=optional_your_tool_categories_here_ex_SERVER_IDE_DEFAULT
TOOL_NAMES=optional_your_tool_names_here_ex_ListProjects

• Use Guide Description Link

alibabacloud-dataworks-mcp-server/
├── src/
│   ├── index.ts          # Main entry point
├── package.json
└── tsconfig.json

The MCP server provides the following DataWorks tools:

See this link

• Keep your private key secure and never share it
• Use environment variables for sensitive information
• Regularly monitor and audit AI agent activities

If you encounter issues:

1. Verify your Aliyun Open API access key and secret key are correct
2. Check your region id is correct
3. Ensure you're on the intended network (mainnet, testnet, or devnet)
4. Verify the build was successful

Key dependencies include:

• @alicloud/dataworks-public20240518
• @alicloud/openapi-client

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

This project is licensed under the Apache 2.0 License.