What programming languages can I use to build an MCP server on Azure Functions?

Develop AI agents that seamlessly interact with real Azure APIs. This asset provides a hub of MCP servers and resources for C#, Python, Java, and JavaScript developers.

Outcomes

What it gets done

Host MCP servers using Azure Functions in multiple languages.

Utilize official MCP SDKs for various programming languages.

Integrate with popular AI frameworks like OpenAI Agents SDK and LangChain.js.

Deploy pre-built MCP servers for data and infrastructure APIs.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-azure-mcp-hub | bash

Overview

Azure MCP Hub MCP Server

The Azure MCP Hub provides a framework and resources for building and running Model Context Protocol (MCP) servers on Azure. These servers expose real-world APIs and tools to AI agents. It supports hosting your own MCP server using Azure Functions in C#, Python, or TypeScript, and offers various plug-and-play MCP servers for data and development infrastructure. Use the Azure MCP Hub when you need to enable AI agents to interact with external services, databases, or development tools. It's ideal for developers building AI-powered applications that require access to real-world data or the ability to perform actions via APIs.

What it does

As an AI developer, I want to enable my AI agents to interact with real-world APIs so that they can perform complex tasks and access external data.

This hub allows you to host your own Model Context Protocol (MCP) server using Azure Functions in your preferred language (C#, Python, or TypeScript). You can also build agents that connect to any MCP server using official SDKs or AI framework integrations. For pre-built solutions, plug-and-play MCP servers expose Data APIs like Redis, PostgreSQL, and MongoDB, as well as Dev & Infra APIs such as Azure CLI, Kubernetes, and GitHub.

These servers are open source and maintained by the community. Microsoft does not review, support, or endorse them. Use at your own discretion.

Source README

Azure Model Context Protocol (MCP) Hub

Build AI agents that call real APIs - fast. Whether you're a C#, Python, Java, or JavaScript developer, this hub helps you build, run, or reuse Model Context Protocol (MCP) servers on Azure to power your AI agents.

🚀 1. Run Your Own MCP Server

Host your own MCP server using Azure Functions - pick your language:

C#
Python
TypeScript

🧠 2. Build Agents That Use MCP

Use official SDKs or your favorite AI frameworks to write agents that connect to any MCP server.

✅ Official MCP SDKs (Build Clients, Servers, or Tools in Any Language)

🤖 AI SDK Integrations

Python: OpenAI Agents SDK - Use MCPServerSse with Azure OpenAI
C#: Semantic Kernel - Add MCP tools to your Kernel instance
JavaScript: LangChain.js - Use MCP tools in LangChain or LangGraph agents
Java: Spring AI - Plug into Spring Boot with auto-config
Azure AI Agents - Add Bing + Azure AI Search to your agent

🧩 3. Use Plug-and-Play MCP Servers

Don't want to build your own tools? These servers expose real APIs via MCP so your agents can just call them.

⚠️ These servers are open source and maintained by the community. Microsoft does not review, support, or endorse them. Use at your own discretion.

🗃️ Data APIs

Redis - Access Azure Redis
PostgreSQL - Query Azure PostgreSQL
MySQL - Use with Azure MySQL
MongoDB - Talk to Cosmos DB with MongoDB
Azure Data Explorer (ADX) - Run KQL queries via agent

🔧 Dev & Infra APIs

Azure CLI - Run CLI commands with natural language
Kubernetes - Control AKS clusters
GitHub - Access GitHub APIs via chat or agent
Azure DevOps (Python) - Work item support
Azure DevOps (Node.js) - Repos, pipelines, and boards

📚 Learn More

📄 Model Context Protocol Spec
🧪 Explore sample agents, tools, and servers in the linked repos
🤝 Contribute a new server or tool via PR!

FAQ

Common questions

Discussion

Build Azure AI Agents with MCP Connectors