by Michael98671
Provides a serverless cloud execution environment for AI agents with standard runtime tools, persistent user state, and real‑time edge‑cloud interaction via MCP.
Offers a one‑click configurable cloud infrastructure that lets AI agent applications run tasks such as browsing, file handling, and terminal operations in a secure, serverless environment on Alibaba Cloud.
{
"mcpServers": {
"wuying_mcp_server": {
"url": "https://agentbay.wuying.aliyun.com/sse?APIKEY=YOUR_API_KEY"
}
}
}
&EXTERNALID=yourUserId
to preserve state across sessions.Q: How many API keys can I create during the public beta? A: Up to 10 API keys per account.
Q: What is the concurrency limit for the free tier? A: 10 simultaneous instances.
Q: Do I need to install any client software? A: No, you only need to add the MCP server JSON to compatible tools (Cursor, Cline, etc.).
Q: How can I keep the cloud environment after a task finishes?
A: Include the EXTERNALID
parameter in the URL to retain the session state.
Q: Where can I find more tool updates? A: Check the official AgentBay service management page linked in the README.
English | 中文
Alibaba Cloud's Wuying AgentBay is a cloud infrastructure designed for Agents in the AI era. It provides enterprises, developers, and AI vendors with a one-click configuration tool and execution environment for AI Agent tasks. Through the Wuying API or AgentBay MCP Server, Agent applications can quickly integrate and utilize relevant tools, running serverlessly in the cloud environment.
Wuying (无影), also known as Alibaba Cloud Workspace, is Alibaba Cloud's innovative cloud-network fusion computing architecture that provides secure and efficient computing experiences through cloud computers, cloud applications and cloud terminals. It features:
AgentBay is Wuying's cloud infrastructure specifically designed for AI Agents. It provides:
Standard Runtime Environment
User State Persistence
Real-time Edge-Cloud Interaction
The service supports calling shared resources, with limited free service during the public beta, and a concurrency limit of 10 instances. Service regions are automatically assigned based on customer access IP.
The service supports built-in Linux version images. Wuying continuously enriches and updates image capabilities while ensuring backward compatibility.
The initial release environment supports the Browser tool, File tool, and Terminal tool by default. For more updates on tools, please visit the official site.
Please create your own API Key.
Note: During the public beta, only 10 API Keys can be created. The created API Key will be displayed in the list on the service management page, and you can copy it for later use.
Confirm the runtime environment and obtain MCP information.
Note: The service supports built-in Linux version images. Wuying continuously enriches and updates image capabilities while ensuring backward compatibility.
Here's an example using Cursor V0.48.9:
Note: Please replace YOUR_API_KEY with the API Key starting with akm- created in Step 1.
Here's an example using the SSE method: The SSE method completes a handshake through an online long connection each time the service is run, without requiring plugin downloads.
{
"mcpServers": {
"wuying_mcp_server": {
"url": "https://agentbay.wuying.aliyun.com/sse?APIKEY=YOUR_API_KEY"
}
}
}
After the task execution is completed, the cloud environment may be released. If you wish to retain related configuration or environment for next time, add the EXTERNALID parameter in the code above. Example:
{
"mcpServers": {
"wuying_mcp_server": {
"url": "https://agentbay.wuying.aliyun.com/sse?APIKEY=YOUR_API_KEY&EXTERNALID=user001"
}
}
}
Support is provided for opening cloud computer screens through the Wuying Web SDK embedded in an iframe or by pulling the Wuying Web client via a browser. When calling the cloud computer screen stream, MCP will return a link with login parameters, formatted as https://wuying.aliyun.com?mcp.html?authcode=<authCode>&resourceId=<resourceId>
.
You can test the effect using built-in prompts like open the browser with wuying-agentbay and access wuying.aliyun.com or similar prompts. If configured correctly, the Wuying cloud environment will be initiated, and browser operations will be executed. During this process, the model will provide a Web link for you to open the Wuying screen stream and take over operations.
MIT
For support and more information, please visit:
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by awslabs
Provides specialized servers that expose AWS capabilities through the Model Context Protocol, enabling AI assistants to retrieve up-to-date documentation, execute API calls, and automate infrastructure workflows directly within development environments.
by cloudflare
Provides a collection of Model Context Protocol servers that enable MCP‑compatible clients to interact with Cloudflare services such as Workers, Observability, Radar, and more, allowing natural‑language driven management of configurations, data, and operations.
by Flux159
Connects to a Kubernetes cluster and offers a unified MCP interface for kubectl, Helm, port‑forwarding, diagnostics, and non‑destructive read‑only mode.
by TencentEdgeOne
Deploy HTML, folders, or zip archives to EdgeOne Pages and instantly obtain a public URL for fast edge delivery.
by rishikavikondala
Provides Model Context Protocol tools for performing AWS S3 and DynamoDB operations, with automatic logging and audit access via the `audit://aws-operations` endpoint.
by confluentinc
Enables AI assistants to manage Confluent Cloud resources such as Kafka topics, connectors, and Flink SQL statements through natural‑language interactions.
by aliyun
Enables AI assistants to operate Alibaba Cloud resources such as ECS, Cloud Monitor, OOS and other services through seamless integration with Alibaba Cloud APIs via the Model Context Protocol.
by heroku
Enables large language models to manage and operate Heroku platform resources directly through the Heroku CLI, exposing a set of tools for app, dyno, add‑on, pipeline, database, and team operations.
by aws-samples
Retrieve PDF documents and other S3 objects through Model Context Protocol resources, enabling LLMs to pull data directly from AWS S3 buckets.