MCP Connector

Automate DataWorks Cloud Resource Operations

MCP server giving AI agents access to Alibaba Cloud's DataWorks Open API for cloud data-resource operations.

Works with alibabacloud

Maintainer of this project? Claim this page to edit the listing.


90
Spark score
out of 100
Updated last month
Version 1.0.0
Models
universal

Add to Favorites

Why it matters

Enable AI agents to interact with and manage Alibaba Cloud DataWorks resources through a standardized Open API interface. This asset facilitates automated operations and data analysis tasks within the Alibaba Cloud ecosystem.

Outcomes

What it gets done

01

Configure DataWorks Open API access for AI agents.

02

Execute DataWorks resource management operations via API.

03

Filter and select specific tools and categories for AI interaction.

04

Manage cloud credentials securely for automated access.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-dataworks | bash

Overview

DataWorks MCP Server

An MCP server exposing Alibaba Cloud's DataWorks Open API to AI agents - metadata exploration, node development, task troubleshooting, and resource management, filterable by tool category or name. Use it to embed DataWorks into a custom MCP client like Cursor or Cline, not for the zero-setup, console-only DataWorks Agent experience.

What it does

DataWorks MCP Server is a Model Context Protocol server that lets AI agents interact with Alibaba Cloud's DataWorks Open API through a standardized interface, built on the Aliyun Open API to perform DataWorks cloud-resource operations. It implements the MCP specification to standardize DataWorks metadata exploration, node development, task troubleshooting, and resource management for any MCP-compatible AI client such as Cursor or Cline - as an alternative to Alibaba Cloud's own hosted DataWorks Agent, which needs no local MCP setup but only works inside the DataWorks console.

When to use - and when NOT to

Use it when you want to embed DataWorks capabilities into your own AI workflow or IDE via a custom MCP client, rather than using the browser-based DataWorks Agent. It is not the right choice for a quick, zero-setup DataWorks experience inside the console itself - that is what DataWorks Agent is for; this server is for teams that specifically need the open MCP protocol integration path into their own tooling.

Capabilities

The server manages DataWorks resources and interacts with the DataWorks Open API, exposing them through the standard MCP tool interface, filterable at connection time via TOOL_CATEGORIES and TOOL_NAMES environment variables - for example a category like SERVER_IDE_DEFAULT or a specific tool like ListProjects. It requires Node.js v16 or higher, a package manager (pnpm recommended, npm or yarn also supported), and a DataWorks Open API access key/secret pair. Configuration is via environment variables: REGION (the DataWorks Open API region ID), ALIBABA_CLOUD_ACCESS_KEY_ID, and ALIBABA_CLOUD_ACCESS_KEY_SECRET. Security guidance: keep the private key secure and never share it, pass credentials via environment variables rather than hardcoding them, and regularly monitor and audit AI agent activity. Key dependencies are @alicloud/dataworks-public20240518 and @alicloud/openapi-client. Building from source instead of installing via npm adds a local development workflow: cloning the repository, installing dependencies with pnpm, building with pnpm run build, and running a dev server (via @modelcontextprotocol/inspector) on http://localhost:5173. The project is released under the Apache 2.0 License.

How to install

npm install -g alibabacloud-dataworks-mcp-server

Who it's for

Developers building custom AI workflows or IDE integrations - Cursor, Cline, and similar MCP clients - that need programmatic access to Alibaba Cloud DataWorks resources. If something goes wrong, troubleshooting steps cover re-verifying the Aliyun access key and secret, confirming the region ID, checking that the client is on the intended network (mainnet, testnet, or devnet), and re-verifying that the build succeeded before reporting an issue.

Source README

MseeP.ai Security Assessment Badge

Try DataWorks Agent

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.

DataWorks Agent This MCP Server
Best for Quick start in the DataWorks console Custom AI clients (Cursor, Cline, etc.)
Setup Open and use in browser Install, configure AK, and connect MCP
Integration Native DataWorks experience Open API via MCP protocol

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

DataWorks MCP Server

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.

Overview

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.

Prerequisites

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

Installation

Option 1: Install from npm (recommend for clients like Cursor/Cline)

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

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

Option 2: Build from Source (for developers)

  1. Clone this repository:
git clone https://github.com/aliyun/alibabacloud-dataworks-mcp-server
cd alibabacloud-dataworks-mcp-server
  1. Install dependencies (pnpm is recommended, npm is supported):
pnpm install
  1. Build the project:
pnpm run build
  1. Development the project (by @modelcontextprotocol/inspector):
pnpm run dev

open http://localhost:5173

Configuration

MCP Server Configuration

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": []
    }
  }
}

Environment Setup

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

Configuration Description

  • Use Guide Description Link

Project Structure

alibabacloud-dataworks-mcp-server/
β”œβ”€β”€ src/
β”‚   β”œβ”€β”€ index.ts          # Main entry point
β”œβ”€β”€ package.json
└── tsconfig.json

Available Tools

The MCP server provides the following DataWorks tools:

See this link

Security Considerations

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

Troubleshooting

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

Dependencies

Key dependencies include:

FAQ

Common questions

Discussion

Questions & comments Β· 0

Sign In Sign in to leave a comment.