How do I install the NuGet package for MCP support in Azure Functions?
Run `dotnet add package Microsoft.Azure.Functions.Worker.Extensions.Mcp --version 1.0.0-preview.2` to add the preview extension.
@0GiS0
Basic information
Crea tu servidor MCP con Azure Functions ⚡️🧰
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-azure-function": {
"command": "npx",
"args": [
"@modelcontextprotocol/inspector",
"http://localhost:7071/runtime/webhooks/mcp/sse"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Azure Functions ⚡️❤️ MCP Servers is a sample repository that demonstrates how to create Model Context Protocol (MCP) servers using Azure Functions and the preview NuGet package Microsoft.Azure.Functions.Worker.Extensions.Mcp. It is designed for developers who want to integrate Azure Functions with MCP and use those servers with GitHub Copilot Chat's agent mode.
Install the NuGet package (dotnet add package Microsoft.Azure.Functions.Worker.Extensions.Mcp --version 1.0.0-preview.2). Run the project locally with func start. Test it using MCP Inspector (npx @modelcontextprotocol/inspector http://localhost:7071/runtime/webhooks/mcp/sse). Configure GitHub Copilot Chat by adding an MCP server entry in .vscode/mcp.json or .vscode/settings.json, using either a local endpoint or a remote Azure Functions URL with the function key. Optionally deploy the function to Azure using the Terraform scripts in the infra directory after creating a terraform.tfvars file with your subscription ID and YouTube API key.
Microsoft.Azure.Functions.Worker.Extensions.Mcp.func start.Run `dotnet add package Microsoft.Azure.Functions.Worker.Extensions.Mcp --version 1.0.0-preview.2` to add the preview extension.
Start the Azure Functions runtime with `func start`, then use `npx @modelcontextprotocol/inspector http://localhost:7071/runtime/webhooks/mcp/sse` to open the MCP inspector.
Create a `.vscode/mcp.json` file with a server entry of type `sse`, pointing to the local or remote URL, and optionally use `inputs` for sensitive values like the function key.
Use the Terraform scripts inside the `infra` folder. After creating a `terraform.tfvars` file with `subscription_id` and `youtube_api_key`, run `terraform init` and `terraform apply`. Then deploy the code using Visual Studio Code or another method.
The server uses SSE (Server-Sent Events) transport. Remote access uses the Azure Functions host key as an authentication header (`x-functions-key`).

Web hosting for websites built with AI. Connect your HostingFor.AI account and your AI assistant can publish and maintain your site directly: upload files, manage DNS records for custom domains, run SQL against your MySQ
Connect Supabase to your AI assistants
Deploy and manage SnapDeploy apps (Docker containers on AWS) from Claude Code, Cursor, Codex or Gemini CLI: builds, logs, env vars, add-ons, domains.
Development environments for coding agents. Enable multiple agents to work safely and independently with your preferred stack.
Comments