Mcp Agentbay
@zhaozeen
Mcp Agentbay について
概要はまだありません
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"agentbay": {
"command": "npx",
"args": [
"-y",
"agentbay-mcp"
],
"env": {
"AGENTBAY_API_KEY": "YOUR_API_KEY_HERE",
"IMAGE_ID": "windows_latest",
"REGION": "singapore"
}
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Mcp Agentbay?
Mcp Agentbay is an MCP server for Alibaba Cloud’s Wuying AgentBay, a cloud infrastructure designed for AI Agents. It provides enterprises, developers, and AI vendors with a one-click configuration tool and serverless execution environment for AI Agent tasks, integrating via SDK or MCP Server.
How to use Mcp Agentbay?
Create an API key in the AgentBay Console, then configure resources by selecting an image in the console and copying the MCP information. Add the code (using SSE or STDIO) to an MCP‑supported client like Cursor. Example SSE configuration: "url": "https://agentbay.wuying.aliyun.com/sse?APIKEY=YOUR_API_KEY". Optionally add an EXTERNALID parameter to retain the environment for future sessions.
Key features of Mcp Agentbay
- One‑click configurable AI Agent task execution
- Pre‑integrated standard MCP tools (Browser, File, Terminal)
- User state persistence with secure isolation of cookies and configurations
- Real‑time edge‑cloud streaming via proprietary ASP protocol
- Serverless scaling to 10,000 concurrent instances
- Enterprise‑grade infrastructure with low‑latency global deployment
Use cases of Mcp Agentbay
- Run AI agents that need browser, file, or terminal access in a secure cloud environment
- Persist user configurations and sessions across multiple agent runs
- Integrate agent tasks with enterprise workflows using SDK or MCP
- Deploy serverless agent tasks that scale on demand
- Use cloud‑streaming to view and control the agent’s cloud desktop in real time
FAQ from Mcp Agentbay
What do I need to start using Mcp Agentbay?
You need an Alibaba Cloud account, an API key (limited to 10 during public beta), a compatible MCP client (e.g., Cursor), and to configure an image via the AgentBay Console.
How can I keep my cloud environment persistent between tasks?
Add an EXTERNALID parameter to the SSE URL (e.g., &EXTERNALID=user001) to retain the configuration and environment for the next session.
How do I view the agent’s cloud screen?
The MCP returns a link like https://wuying.aliyun.com?mcp.html?authcode=<code>&resourceId=<id>. Open it in a browser to stream the cloud desktop. The link has limited validity and should be used immediately.
What tools are available in the initial release?
The environment supports the Browser, File, and Terminal MCP tools by default. More tools are added over time (see the official site).
Are there any usage limits during the public beta?
Yes: you can create up to 10 API keys, the service supports a concurrency limit of 10 instances, and free usage is partially limited. Regions are assigned based on the client IP.
「AI とエージェント」の他のコンテンツ
1MCP - One MCP Server for All
1mcp-appA unified Model Context Protocol server implementation that aggregates multiple MCP servers into one.
Perplexity MCP Server
DaInfernalCoderA Model Context Protocol (MCP) server for research and documentation assistance using Perplexity AI. Won 1st @ Cline Hackathon
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
コメント