MCP.so
登录

Secure Remote MCP Servers using Azure API Management

@Azure-Samples

基本信息

分类

开发工具

许可证

MIT

传输方式

stdio

作者

Azure-Samples

关于 Secure Remote MCP Servers using Azure API Management

Azure API Management as AI Gateway to Remote MCP servers.

Secure Remote MCP Servers using Azure API Management 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "remote-mcp-apim-functions-python": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector"
      ]
    }
  }
}

Secure Remote MCP Servers using Azure API Management 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Secure Remote MCP Servers using Azure API Management?

This is an experimental sample that uses Azure API Management as an AI Gateway for MCP (Model Context Protocol) servers. It implements the latest MCP Authorization specification, deploying a secure multi-layered MCP server infrastructure on Azure with authentication, authorization, and request routing managed through Azure API Management.

How to use Secure Remote MCP Servers using Azure API Management?

Deploy the infrastructure using the azd up command after registering the Microsoft.App resource provider. Then connect an MCP client (e.g., MCP Inspector) using SSE transport to the API Management SSE endpoint displayed after deployment.

Key features of Secure Remote MCP Servers using Azure API Management

  • OAuth 2.0/PKCE authentication flow per MCP specification
  • Encrypted session keys for secure API access
  • Multi-layer security with API Management, Functions, and managed identities
  • Serverless compute using Azure Functions (Python 3.11)
  • Optional VNet integration for network isolation
  • Centralized policy management for rate limiting and throttling

Use cases of Secure Remote MCP Servers using Azure API Management

  • Hosting secure MCP servers with OAuth-protected tool access
  • Implementing an enterprise-grade AI Gateway for MCP clients
  • Enabling third-party authorization flows for MCP tools
  • Deploying a reference architecture for remote MCP servers on Azure

常见问题

1

What runtime does the MCP server use?

The MCP server runs on Azure Functions with Python 3.11 on the Flex Consumption plan.

2

What transport protocol does the MCP server use?

The MCP server uses Server-Sent Events (SSE) transport, with the endpoint at `/mcp/sse`.

3

How is authentication handled?

Authentication follows the MCP Authorization specification using OAuth 2.0 with PKCE, integrated with Entra ID (Azure Active Directory). Session keys are encrypted and stored in API Management cache.

4

What is the role of Azure API Management?

API Management acts as the central security gateway, handling OAuth flows, request validation, header injection, and secure proxying to the backend Azure Function.

5

Where can I deploy and test the server?

Deploy using `azd up` from the GitHub sample repository. Test with the MCP Inspector tool by connecting to the SSE endpoint.

评论

开发工具 分类下的更多 MCP 服务器