Advertise
MCP.so
Sign In

Getting Started with Remote MCP Servers using Azure Functions (P…

@raorugan

Repository

Basic information

Category

Cloud & Infrastructure

Transports

stdio

Author

raorugan

About Getting Started with Remote MCP Servers using Azure Functions

MCP server sample travel buddy app hosted on Azure Functions on Azure Container Apps and MCP extension

Getting Started with Remote MCP Servers using Azure Functions config

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

{
  "mcpServers": {
    "MCPonFuncOnACA": {
      "command": "docker",
      "args": [
        "run",
        "-p",
        "10000:10000",
        "-p",
        "10001:10001",
        "-p",
        "10002:10002",
        "\\"
      ]
    }
  }
}

Getting Started with Remote MCP Servers using Azure Functions tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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

Overview

What is Getting Started with Remote MCP Servers using Azure Functions (Python)?

A quickstart template to build and deploy a custom remote MCP server to Azure Functions using Python. It is secured by design with keys and HTTPS, and supports options for OAuth, API Management, and VNET isolation.

How to use Getting Started with Remote MCP Servers using Azure Functions (Python)?

Set up prerequisites: Python 3.11+, Azure Functions Core Tools, and Azurite storage emulator. Run locally by changing to src, running pip install -r requirements.txt, then func start. Connect clients via VS Code Copilot Edits or MCP Inspector using the SSE endpoint http://localhost:7071/runtime/webhooks/mcp/sse. Deploy to Azure with azd up or through Azure Container Apps documentation.

Key features of Getting Started with Remote MCP Servers using Azure Functions (Python)

  • Quickstart template for a remote MCP server
  • Built with Azure Functions and Python
  • Secure by design with keys and HTTPS
  • Supports local development and cloud deployment
  • Includes sample travel MCP tools via RapidAPI
  • Options for OAuth, API Management, and VNET isolation

Use cases of Getting Started with Remote MCP Servers using Azure Functions (Python)

  • Build a custom remote MCP server for LLM tools
  • Securely expose MCP endpoints in Azure
  • Integrate travel APIs as MCP tools
  • Experiment with remote MCP servers using Azure Functions

Frequently asked questions

1

What prerequisites are needed?

Python 3.11 or higher, Azure Functions Core Tools, and an Azure Storage emulator (Azurite). Visual Studio Code with the Azure Functions extension is optional for local debugging.

2

How do I run the server locally?

Start Azurite, then in the `src` folder run `pip install -r requirements.txt` followed by `func start`. The server listens on `http://localhost:7071/runtime/webhooks/mcp/sse`.

3

How do I connect an MCP client?

Use the SSE transport with the endpoint URL. For local testing, the URL is `http://localhost:7071/runtime/webhooks/mcp/sse`. For remote access, include the system key as a `code` query parameter or as the `x-functions-key` header.

4

How do I deploy to Azure?

Run `azd up` in the project root, or follow the Azure documentation to provision Azure Functions on Azure Container Apps. The deployed endpoint will be secured with a system key by default.

5

What sample tools are included?

Two MCP tools are defined: `get_attractions` and `get_attractions_reviews`, which call the RapidAPI Booking.com API to retrieve travel details.

Comments

More Cloud & Infrastructure MCP servers

Kubernetes MCP Server

manusa

Model Context Protocol (MCP) server for Kubernetes and OpenShift

1.8K

Tessryx

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.

HostingFor.AI

J. Klassen Inc.

Web hosting for websites built with AI. Connect your HostingFor.AI account and your AI assistant can publish and maintain your site directly: upload files, manage DNS records for custom domains, run SQL against your MySQ

Backblaze B2 MCP server

backblaze-labs

MCP server for Backblaze B2 Cloud Storage: a focused, safe 40-tool surface (17 native B2 SDK, 19 S3 data-plane, 4 analytics) for any MCP-compatible AI client, currently incubating in Backblaze-Labs

2

Kilo IoT Platform

Kilo IoT

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a

Advertise