Remote MCP Functions
Getting Started with Remote MCP Servers using Azure Functions (Python)
What is Remote MCP Functions?
Remote MCP Functions is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to getting started with remote mcp servers using azure functions (python)
Getting Started with Remote MCP Servers using Azure Functions (Python)
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Getting Started with Remote MCP Servers using Azure Function
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx remote-mcp-functions-pythonConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Remote MCP Functions
Remote MCP Functions Python is an Azure Samples reference implementation that shows how to deploy production-ready MCP servers as Azure Functions using Python. It provides four sample MCP server applications — covering CRUD tools, QR code generation, MCP Resources, MCP Prompts, and an interactive weather demo — all secured with Microsoft Entra authentication. Developers use it as a starting point to host their own remote MCP endpoints in the cloud, accessible from any MCP client that supports HTTP/SSE transport.
Prerequisites
- Python 3.13 or later
- Azure Functions Core Tools 4.8.0 or later
- Azure Developer CLI (azd) version 1.23.x or later
- Docker installed (used by the Azurite storage emulator for local development)
- An Azure subscription with permission to create Function Apps and Microsoft Entra app registrations
Clone the sample repository
Clone the Azure Samples repository to your local machine and navigate into it.
git clone https://github.com/Azure-Samples/remote-mcp-functions-python.git
cd remote-mcp-functions-pythonLog in to Azure and provision resources
Use the Azure Developer CLI to authenticate and provision all required Azure resources (Function App, Storage Account, Entra app registration) with a single command.
azd auth login
azd upRun locally for development
Start the Azure Functions runtime locally. Azurite must be running to emulate storage. The functions will be available at localhost:7071.
# Start Azurite in a separate terminal
docker run -p 10000:10000 -p 10001:10001 -p 10002:10002 mcr.microsoft.com/azure-storage/azurite
# Start the Functions host
func startConfigure your MCP client to connect
Add the deployed Azure Function URL as an MCP server in your client configuration. Use the HTTPS endpoint returned by `azd up`, which is protected by Microsoft Entra.
{
"mcpServers": {
"azure-mcp": {
"url": "https://<your-function-app>.azurewebsites.net/mcp"
}
}
}Explore the four sample MCP servers
The repo ships four distinct sample apps: FunctionsMcpTool (CRUD + QR tools), FunctionsMcpResources (resource templates), FunctionsMcpPrompts (code review and doc generation prompts), and McpWeatherApp (interactive UI demo). Each is a separate Function App entry point.
Remote MCP Functions Examples
Client configuration (remote Azure Function endpoint)
Connecting Claude Desktop to a deployed Azure Functions MCP server over HTTPS.
{
"mcpServers": {
"azure-remote-mcp": {
"url": "https://<your-function-app>.azurewebsites.net/mcp"
}
}
}Prompts to try
Example prompts for the sample Azure Functions MCP servers.
- "Generate a QR code for https://example.com and return it as a data URI."
- "Create a new snippet with title 'Hello' and content 'Hello, world!'."
- "List all stored snippets."
- "Run the code review checklist prompt on the following Python function: ..."
- "What is the current weather in Seattle?"Troubleshooting Remote MCP Functions
azd up fails with permission errors on Entra app registration
Your Azure account must have the Application Administrator or Global Administrator role in the Entra tenant to create app registrations. Ask your tenant admin to grant this role or pre-create the app registration and supply its client ID to the deployment.
Local func start fails because storage emulator is unavailable
Start Azurite with Docker before running func start. The Functions host requires a storage emulator even for HTTP-triggered functions during local development.
MCP client gets 401 Unauthorized from the deployed Function URL
The sample uses Microsoft Entra authentication. Ensure your client is configured to pass a valid Bearer token. For testing, you can retrieve a token with `az account get-access-token` and add it as an Authorization header.
Frequently Asked Questions about Remote MCP Functions
What is Remote MCP Functions?
Remote MCP Functions is a Model Context Protocol (MCP) server that getting started with remote mcp servers using azure functions (python) It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Remote MCP Functions?
Follow the installation instructions on the Remote MCP Functions GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Remote MCP Functions?
Remote MCP Functions works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Remote MCP Functions free to use?
Yes, Remote MCP Functions is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Remote MCP Functions Alternatives — Similar Cloud Services Servers
Looking for alternatives to Remote MCP Functions? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Remote MCP Functions in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Remote MCP Functions?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.