alibabacloud-api
阿里云 MCP Server 是一个强大的云服务集成平台,通过 Model Context Protocol (MCP) 为 AI 应用提供阿里云服务的无缝集成能力。该平台支持数万个阿里云 OpenAPI,让开发者能够轻松地将阿里云的各种服务能力集成到 AI 工作流中。
claude mcp add --transport stdio aliyun-alibabacloud-api-mcp-server node path/to/server.js \ --env ALIBABA_CLOUD_ACCESS_KEY_ID="your_access_key_id" \ --env ALIBABA_CLOUD_ACCESS_KEY_SECRET="your_secret_key"
How to use
This MCP server provides seamless integration with Alibaba Cloud OpenAPI services through the MCP (Model Context Protocol) framework. It supports both remote (cloud-hosted) access and local (stdio-based) operation. The server enables AI applications to call tens of thousands of Alibaba Cloud OpenAPIs, with OAuth 2.0 authentication and a focus on OpenAPI customization, multi-account support, and governance features. Use the local mode for data security and customization by running the MCP server as a standalone process and communicating via standard input/output, or connect through the remote hosted mode for zero-maintenance access to Alibaba Cloud services.
To use the server, configure your Alibaba Cloud credentials (via environment variables or your preferred secret manager) and start the local MCP server. In local mode, you can leverage the provided capabilities such as OpenAPI customization (to tailor API descriptions for AI consumption), parameter simplification, and improved API call reliability. If you need multi-account scenarios, leverage the multi-account support to switch or assume roles as needed. For authentication, set up OAuth with token lifecycles and optional white-listed callback URLs as described in the capabilities, enabling secure, long-lived access where appropriate.
How to install
Prerequisites:
- Node.js and npm (or yarn)
- Git
Install steps:
-
Clone the repository locally git clone https://github.com/aliyun/[具体服务仓库名称] cd [仓库目录]
-
Install dependencies npm install # or yarn install
-
Configure credentials (example using environment variables) export ALIBABA_CLOUD_ACCESS_KEY_ID=your_access_key export ALIBABA_CLOUD_ACCESS_KEY_SECRET=your_secret_key
-
Start the MCP server (local mode) npm start # or follow the repository's specific startup command
-
Validate locally by sending a test request through the MCP interface or your AI application integration.
Notes:
- If the repository provides alternative startup scripts, follow those instructions and adjust the command in mcp_config accordingly.
- For remote mode usage, refer to the remote endpoint configuration in the official docs and your cloud provider setup.
Additional notes
Tips and common considerations:
- Ensure your Alibaba Cloud credentials have the necessary permissions for the desired OpenAPI calls.
- In local mode, keep credentials secure and consider using a secret manager or environment isolation for development environments.
- If you switch from local to remote mode, update the mcp_config to point to the remote service and adjust authentication flow accordingly.
- Check region-specific endpoints if you are targeting China vs International endpoints (e.g., https://api.aliyun.com/mcp vs https://api.alibabacloud.com/mcp).
- When enabling advanced features like OpenAPI customization or Terraform-as-Tools, review the corresponding documentation to understand parameter mappings and AI-friendly API descriptions.
Related MCP Servers
Wax
Sub-Millisecond RAG on Apple Silicon. No Server. No API. One File. Pure Swift
wanaku
Wanaku MCP Router
mcp
Octopus Deploy Official MCP Server
mem0
✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.
furi
CLI & API for MCP management
Pare
Dev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.