Mcponfunconaca

🚀 Remote MCP Server with Azure Functions (Python)

This is a quick - start template for easily building and deploying a custom remote MCP server to the cloud using Azure Functions and Python. The MCP server, with experimental feature support, can serve as a tool for large language models (LLMs).

🚀 Quick Start

This is a quick - start template for easily building and deploying a custom remote MCP server to the cloud using Azure Functions and Python. The MCP server, with experimental feature support, can be provided as a tool for large language models (LLMs). The MCP feature needs to be enabled in the function app and can reference the experimental bundle in host.json.

{
  "extensions": {
    "httpExtension": {},
    "mcpExtension": {}
  },
  "extensionBundle": {
    "id": "Microsoft.Azure.Functions.ExtensionBundle.Experimental",
    "version": "[4.*, 5.0.0)"
  }
}

✨ Features

• Build and deploy a custom remote MCP server using Azure Functions and Python.
• Provide MCP tools for large language models (LLMs) through experimental features.

📦 Installation

Prerequisites

• Basic understanding of Azure Functions and Python.
• Installed and configured Azure CLI.
• An Azure account and subscription.

Create a Function App

Use the azd command to create a new Azure Functions app and specify the runtime as Python:

azd init --name <your_function_app_name> --location <region> --runtime python

Navigate to the project directory and initialize mcp.json and other necessary files:

cd . && azd up

Configure the MCP Server

Enable experimental features and the MCP extension in host.json:

{
  "extensions": {
    "httpExtension": {},
    "mcpExtension": {}
  },
  "extensionBundle": {
    "id": "Microsoft.Azure.Functions.ExtensionBundle.Experimental",
    "version": "[4.*, 5.0.0)"
  }
}

Define MCP tools in mcp.json:

{
  "myMCPTool": {
    "type": "functionTrigger",
    "description": "Retrieve attractions at a search location.",
    "properties": {},
    "trigger": {
      "funcName": "get_attractions"
    }
  }
}

Create a Function

Create a Python function file (e.g., function_app.py) in the src directory and add the following code:

import logging
import json

def get_attractions(context):
    """
    Retrieves attractions at a search location using the RapidAPI endpoint.

    Args:
        context: The trigger context containing the input arguments.

    Returns:
        str: A JSON string containing the attractions or an error message.
    """
    content = json.loads(context)
    query = content["arguments"].get("query", "").strip()
    language_code = content["arguments"].get("languagecode", "en-us").strip()

    # Add your logic to call RapidAPI here

    return json.dumps({
        "result": "Success",
        "message": f"Successfully retrieved attractions for {query}"
    })

def hello_mcp(context):
    """
    A simple function that returns a greeting message.

    Args:
        context: The trigger context (not used in this function).

    Returns:
        str: A greeting message.
    """
    return "Hello I am MCPTool!"

Deploy to Azure

Use the azd command to deploy the project to Azure:

azd up

This will create all the necessary Azure resources, including the function app, storage account, and API management instance.

💻 Usage Examples

Basic Usage

After deployment, you can access the MCP server from VS Code or any compatible client. Configure the tools through mcp.json and access them using the following URL:

https://<your_function_app_name>.azurewebsites.net/runtime/webhooks/mcp/sse

📚 Documentation

Notes

• Use API Management to improve security.
• Enable built - in authentication to support OAuth providers.
• Enable VNET using the VNET_ENABLED=true flag.

Next Steps

• Add API Management to your MCP server.
• Enable built - in authentication on your MCP server.
• Enable VNET using the VNET_ENABLED=true flag.
• Learn more about Microsoft's related MCP efforts.