What dependencies are required?
Azure CLI, Node.js (for npx), and Python with packages from `requirements.txt` are needed.
@ninefyi
基本情報
Introduction to the Azure MCP Server
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": {
"global-az-thailand-25": {
"command": "npx",
"args": [
"-y",
"@azure/mcp@latest",
"server",
"start",
"--transport",
"sse"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Global Azure Thailand 2025 is an online event held on 10 May 2025 that introduces the Azure MCP Server. It explains how to set up and run the Azure MCP Server with Azure OpenAI, using SSE transport and Python examples.
Install Azure CLI, log in with az login, create a .env file with Azure OpenAI credentials, install Python dependencies from requirements.txt, start the Azure MCP Server via npx -y @azure/mcp@latest server start --transport sse, then run python mcp_sse_simple.py or python mcp_sse_gradio.py.
Azure CLI, Node.js (for npx), and Python with packages from `requirements.txt` are needed.
First log in with `az login`, then provide Azure OpenAI API key, endpoint, deployment, and API version in the `.env` file.
The server is started with `--transport sse`.
In a `.env` file containing `AZURE_OPENAI_API_KEY`, `AZURE_OPENAI_ENDPOINT`, `AZURE_OPENAI_DEPLOYMENT`, and API version variables.
MCP server connecting to Kubernetes

Build and run websites, APIs, automations, and admin tools from chat. Your agent creates the data, logic, pages, and scheduled jobs; Tessryx hosts them on your own domain. No code generated, nothing to deploy.
Put the project you are working on online. Deploys the current folder or a GitHub repo to a live HTTPS URL on Dockhold; reads status and logs, sets variables, resizes apps and databases...
Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
コメント