Azure-Samples/remote-mcp-functions-dotnet

Getting Started with Remote MCP Servers using Azure Functions (.NET/C#)

This is a quickstart template to easily build and deploy a custom remote MCP server to the cloud using Azure functions. 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 configured with built-in authentication using Microsoft Entra as the identity provider.

You can also use API Management to secure the server, as well as network isolation using VNET.

If you're looking for this sample in more languages check out the Node.js/TypeScript and Python samples.

Prerequisites

Required for all development approaches

• .NET 10 SDK
• Azure Functions Core Tools >= 4.0.7030
• Azure Developer CLI (for deployment)

For Visual Studio development

• Visual Studio 2022
• Make sure to select the Azure development workload during installation

For Visual Studio Code development

• Visual Studio Code
• Azure Functions extension

Choose one: You can use either Visual Studio OR Visual Studio Code. Both provide full debugging support, but the setup steps differ slightly.

Below is the architecture diagram for the Remote MCP Server using Azure Functions:

Prepare your local environment

An Azure Storage Emulator is needed for this particular sample because we will save and get snippets from blob storage. Start Azurite emulator:

docker run -d -p 10000:10000 -p 10001:10001 -p 10002:10002 \
    mcr.microsoft.com/azure-storage/azurite

Note if you use Azurite coming from VS Code extension you need to run Azurite: Start now or you will see errors.

Run and test locally

MCP Functions Tool

Step 1: Start the Functions host

From the src/FunctionsMcpTool folder, run this command to start the Functions host locally:

cd src/FunctionsMcpTool
func start

Step 2: Connect to the MCP server

You can connect to your local MCP server using VS Code with GitHub Copilot or MCP Inspector.

Option A: VS Code with GitHub Copilot

1. Open .vscode/mcp.json. Find the server called local-mcp-function and click Start above the name. The server is already set up with the running Function app's MCP endpoint:

   http://localhost:7071/runtime/webhooks/mcp
   

2. In Copilot chat agent mode enter a prompt to trigger the tool, e.g., select some code and enter this prompt

   Say Hello 
   

   Save this snippet as snippet1 
   

   Retrieve snippet1 and apply to NewFile.cs
   

3. When prompted to run the tool, consent by clicking Continue

4. When you're done, press Ctrl+C in the terminal window to stop the func.exe host process.

Option B: MCP Inspector

1. In a new terminal window, install and run MCP Inspector

   npx @modelcontextprotocol/inspector
   

2. CTRL click to load the MCP Inspector web app from the URL displayed by the app (e.g. http://0.0.0.0:5173/#resources)

3. Set the transport type to Streamable HTTP

4. Set the URL to your running Function app's MCP endpoint and Connect:

   http://0.0.0.0:7071/runtime/webhooks/mcp
   

5. List Tools. Click on a tool and Run Tool.

Verify local blob storage (optional)

After testing the snippet save functionality locally, you can verify that blobs are being stored correctly in your local Azurite storage emulator.

Using Azure Storage Explorer:

1. Open Azure Storage Explorer
2. In the left panel, expand Emulator & Attached → Storage Accounts → (Emulator - Default Ports) (Key)
3. Navigate to Blob Containers → snippets
4. You should see any saved snippets as blob files in this container
5. Double-click on any blob to view its contents and verify the snippet data was saved correctly

Using Azure CLI (alternative):

# List blobs in the snippets container
az storage blob list --container-name snippets --connection-string "DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;BlobEndpoint=http://127.0.0.1:10000/devstoreaccount1;"

# Download a specific blob to view its contents
az storage blob download --container-name snippets --name <blob-name> --file <local-file-path> --connection-string "DefaultEndpointsProtocol=http;AccountName=devstoreaccount1;AccountKey=Eby8vdM02xNOcqFlqUwJPLlmEtlCDXJ1OUzFT50uSRZ6IFsuFq2UVErCz4I6tq/K1SZFPTOtr/KBHBeksoGMGw==;BlobEndpoint=http://127.0.0.1:10000/devstoreaccount1;"

Weather MCP App

This repository also includes a Weather App sample that demonstrates MCP tools with an interactive UI. See for details.

1. Build the UI:

   cd src/McpWeatherApp/app
   npm install
   npm run build
   cd ..
   

2. Run the function app:

   func start
   

3. In .vscode/mcp.json, click Start above local-mcp-function

4. Ask Copilot: "What's the weather in Seattle?"

Deploy to Azure

Stop the local server with Ctrl+C and switch back to the root directory.

Step 1: Sign in to Azure

az login
azd auth login

Step 2: Create an environment and configure

azd env new <environment-name>

Configure VS Code as an allowed client application to request access tokens from Microsoft Entra:

azd env set PRE_AUTHORIZED_CLIENT_IDS aebc6443-996d-45c2-90f0-388ff96faa56

Optional: Enable VNet isolation:

azd env set VNET_ENABLED true

Step 3: Deploy

Deploy both apps:

azd up

Or deploy a specific app:

# Deploy only the MCP Tool (with Entra auth)
azd deploy api

# Deploy only the Weather App (no auth)
azd deploy weather

Step 4: Connect to the remote MCP server

After deployment finishes, open .vscode/mcp.json and click Start above remote-mcp-function. You'll be prompted for functionapp-name (find it in your azd command output or /.azure/*/.env file). You'll also be prompted to authenticate with Microsoft—click Allow and login with your Azure subscription email.

[!TIP] Successful connect shows the number of tools the server has. You can see more details on the interactions between VS Code and server by clicking on More... -> Show Output above the server name.

Redeploy and clean up

Redeploy all: Run azd up as many times as needed to deploy code updates.

Redeploy one service: Use azd deploy api or azd deploy weather to redeploy a specific app.

Clean up: Delete all Azure resources when done:

azd down

Source Code

The function code for the GetSnippet and SaveSnippet endpoints are defined in . The McpToolsTrigger attribute applied to the async Run method exposes the code function as an MCP Server.

The following shows the code for a few MCP server examples (get string, get object, save object):

[Function(nameof(GetSnippet))]
public object GetSnippet(
    [McpToolTrigger(GetSnippetToolName, GetSnippetToolDescription)] ToolInvocationContext context,
    [BlobInput(BlobPath)] string snippetContent)
{
    return snippetContent;
}

[Function(nameof(SaveSnippet))]
[BlobOutput(BlobPath)]
public string SaveSnippet(
    [McpToolTrigger(SaveSnippetToolName, SaveSnippetToolDescription)] ToolInvocationContext context,
    [McpToolProperty(SnippetNamePropertyName, PropertyType, SnippetNamePropertyDescription)] string name,
    [McpToolProperty(SnippetPropertyName, PropertyType, SnippetPropertyDescription)] string snippet)
{
    return snippet;
}

[Function(nameof(SayHello))]
public string SayHello(
    [McpToolTrigger(HelloToolName, HelloToolDescription)] ToolInvocationContext context
)
{
    logger.LogInformation("C# MCP tool trigger function processed a request.");
    return "Hello I am MCP Tool!";
}

Next Steps

• Add API Management to your MCP server
• Enable VNET using VNET_ENABLED=true flag
• Learn more about related MCP efforts from Microsoft

Troubleshooting