remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Integrations
Azure Functions support for the MCP implementation, providing serverless compute functionality for the MCP authorization flow.
Allows implementation of MCP servers using Python, mentioned as one of the languages used in the sample.
Secure Remote MCP Servers using Azure API Management (Experimental)
Azure API Management acts as the AI Gateway for MCP servers.
This sample implements the latest MCP Authorization specification
This is a sequence diagram to understand the flow.
Deploy Remote MCP Server to Azure
- Register
Microsoft.Appresource provider.- If you are using Azure CLI, run
az provider register --namespace Microsoft.App --wait. - If you are using Azure PowerShell, run
Register-AzResourceProvider -ProviderNamespace Microsoft.App. Then run(Get-AzResourceProvider -ProviderNamespace Microsoft.App).RegistrationStateafter some time to check if the registration is complete.
- If you are using Azure CLI, run
- Run this azd command to provision the api management service, function app(with code) and all other required Azure resourcesCopy
MCP Inspector
- In a new terminal window, install and run MCP InspectorCopy
- CTRL click to load the MCP Inspector web app from the URL displayed by the app (e.g. http://127.0.0.1:6274/#resources)
- Set the transport type to
SSE - Set the URL to your running API Management SSE endpoint displayed after
azd upand Connect:Copy - List Tools. Click on a tool and Run Tool.
This server cannot be installed
Acts as an AI Gateway for MCP servers using Azure API Management, implementing the latest MCP Authorization specification.