Pieter de Bruin

Model Context Protocol (MCP) is a way for apps to provide capabilities and context to a large language model. A key feature of MCP is the ability to define tools that AI agents can leverage to accomplish whatever tasks they’ve been given. MCP servers can be run locally, but remote MCP servers are important for sharing tools that work at cloud scale.

Remote MCP quickstarts in Python, Node.js (TypeScript), and .NET (C#) are a preview of triggers and bindings that allow you to build tools using remote MCP with server-sent events (SSE) with Azure Functions.

Blog post header showing Azure Functions logo with MCP connection icon and title Build AI agent tools using remote MCP with Azure Functions

Blog post

Repo

Thanks for reading! :-)

You May Also Enjoy

GitHub Copilot CLI for beginners

Copilot in IDE vs CLI? You can have both! VS Code works with GitHub Copilot agent mode AND GitHub Copilot CLI works in the terminal. Actually nowadays I wor...

AI agent skills

Have you experimented with AI agent skills? MCP Servers and skills combine really well, since MCP Servers provide knowledge and skills provide behavior. Lea...

Chat with an API

Did you know you can chat with an API?! The Azure Functions team recently published a blog post about hosting declarative markdown agents. It goes into MCP c...