alibabacloud-dataworks
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.
claude mcp add --transport stdio aliyun-alibabacloud-dataworks-mcp-server npx -y alibabacloud-dataworks-mcp-server \ --env REGION="your_dataworks_open_api_region_id_here" \ --env TOOL_NAMES="optional_your_tool_names_here_ex_ListProjects" \ --env TOOL_CATEGORIES="optional_your_tool_categories_here_ex_SERVER_IDE_DEFAULT" \ --env ALIBABA_CLOUD_ACCESS_KEY_ID="your_alibaba_cloud_access_key_id" \ --env ALIBABA_CLOUD_ACCESS_KEY_SECRET="your_alibaba_cloud_access_key_secret"
How to use
This MCP server provides a standardized interface for interacting with Alibaba Cloud DataWorks resources via the DataWorks Open API. It exposes a set of tools that allow AI agents to perform common cloud resource operations in a consistent, protocol-driven manner. By using the MCP framework, you can query projects, pipelines, and other DataWorks resources, as well as perform actions exposed by the underlying tools. The server is designed to be pluggable: you can adjust which tools are available through TOOL_CATEGORIES and TOOL_NAMES, or swap in a different provider if needed. To begin, configure your environment with your DataWorks region and credentials, then deploy the MCP server and connect your AI agent to the MCP interface to start issuing actions.
How to install
Prerequisites:
- Node.js v16 or higher
- npm, pnpm, or yarn (pnpm recommended)
- DataWorks Open API access key and secret key
Option A: Install from npm (recommended for clients like Cursor/Cline)
- Install globally:
npm install -g alibabacloud-dataworks-mcp-server
- Start the server (example):
alibabacloud-dataworks-mcp-server
Option B: Build from source (developers)
- Clone the repository:
git clone https://github.com/aliyun/alibabacloud-dataworks-mcp-server
cd alibabacloud-dataworks-mcp-server
- Install dependencies (pnpm is recommended, npm is supported):
pnpm install
- Build the project:
pnpm run build
- Run in development mode (with inspector):
pnpm run dev
Open http://localhost:5173 to verify the server is running.
Additional notes
Environment variables are sensitive. Use env files or secure secrets management in production. Ensure your DataWorks Open API region (REGION) matches the region of your DataWorks resources. If you restrict tools, set TOOL_CATEGORIES and TOOL_NAMES accordingly. When upgrading the MCP server, revalidate your credentials and the open API permissions. If you encounter network or build issues, verify Node.js version compatibility and reinstall dependencies as needed.
Related MCP Servers
netdata
The fastest path to AI-powered full stack observability, even for lean teams.
core
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
anyquery
Query anything (GitHub, Notion, +40 more) with SQL and let LLMs (ChatGPT, Claude) connect to using MCP
wren-engine
🤖 The Semantic Engine for Model Context Protocol(MCP) Clients and AI Agents 🔥
pgmcp
An MCP server to query any Postgres database in natural language.
nasdaq-data-link
A Nasdaq Data Link MCP (Model Context Protocol) Server