Secure Remote MCP Servers using Azure API Management

@Azure-Samples

About Secure Remote MCP Servers using Azure API Management

Azure API Management as AI Gateway to Remote MCP servers.

Config

Add this server to your MCP-compatible client using the configuration below.

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

FAQ from Secure Remote MCP Servers using Azure API Management

What runtime does the MCP server use?

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

What transport protocol does the MCP server use?

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

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.

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.

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.

Frequently asked questions

What runtime does the MCP server use?

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

What transport protocol does the MCP server use?

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

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.

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.

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.

Comments

Basic information

More Developer Tools MCP servers

MCP Containers

metorial

Connect any AI model to 1200+ integrations (MCP, CLI, API)

3.3K

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

endoflife.ai

Free MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 485 tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up

mcp-excalidraw

yctimlin

MCP server and Claude Code skill for Excalidraw — programmatic canvas toolkit to create, edit, and export diagrams via AI agents with real-time canvas sync.

2.1K