Getting Started with Agent Service and Remote MCP Servers (Python)

This is a quickstart template to easily run an Azure AI Foundry Agent Service client and then add a custom remote MCP server to the cloud using Azure Functions Remote MCP. You can clone/restore/run on your local machine with debugging, and azd up to have it in the cloud in a couple minutes. The MCP server is secured by design using keys and HTTPS, and allows more options for OAuth using built-in auth and/or API Management as well as network isolation using VNET.

If you're looking for this sample in more languages check out the .NET/C# and Node.js/TypeScript versions.

Below is the architecture diagram for the Remote MCP Server using Azure Functions with Foundry Agent Service:

Prerequisites

• Python version 3.11 or higher
• Azure Functions Core Tools >= 4.0.7030
• Azure Developer CLI
• To use Visual Studio Code to run and debug locally:
  • Visual Studio Code
  • Azure Functions extension

Deploy Remote MCP Server to Azure

Run this azd command to provision the function app, with any required Azure resources including AI Foundry Agent Service, and deploy your code:

azd up

Note: You'll be prompted to specify an agentLocation during deployment. This must be one of the AI Foundry supported regions: westus, westus2, uaenorth, southindia, or switzerlandnorth. This location is used specifically for AI resources (AI Services, Search, Cosmos DB) and can be different from your main deployment location.

Additionally, API Management can be used for improved security and policies over your MCP Server, and App Service built-in authentication can be used to set up your favorite OAuth provider including Entra.

Connect to your remote MCP server function app from a client

Your client will need a key in order to invoke the new hosted SSE endpoint, which will be of the form https://<funcappname>.azurewebsites.net/runtime/webhooks/mcp/sse. The hosted function requires a system key by default which can be obtained from the portal or the CLI (az functionapp keys list --resource-group <resource_group> --name <function_app_name>). Obtain the system key named mcp_extension.

Foundry Agent Service Client

1. Change to the agent folder in a new terminal window:

   cd agent
   

2. Create a .env file based on the example provided. Copy the .env.example file:

   copy .env.example .env
   

3. Edit the .env file with your deployed function app details:

   # Azure AI Project Configuration
   PROJECT_ENDPOINT=https:
   

... View full README on GitHub