Azure-Samples/mcp-agent-langchainjs

View on GitHub ↗

Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger restaurant

197 ★94 forksTypeScriptUpdated 1mo ago

What you need to know

Azure sample demonstrating an AI agent built with LangChain.js that uses MCP tool calling to interact with a burger ordering API

Install

npm install
npm start

Usage

  • •Deploy with azd up or run locally with Ollama for a zero-cloud setup
  • •Ask the agent things like "What spicy burgers do you have?" or "Order two Classic Cheeseburgers"

Key features

  • ✓LangChain.js agent with tool calling via MCP (Streamable HTTP transport)
  • ✓Multi-service architecture: web UIs, agent API, burger API, burger MCP server
  • ✓User authentication with session history and 100% serverless deployment
  • ✓Works with GitHub Copilot, Claude and other MCP-compatible clients

Best for

Developers learning how to build MCP-powered AI agents with LangChain.js on Azure

Caveats

  • ⚠Local runs use in-memory storage - data lost on restart
  • ⚠Requires Node.js 22+ and optional Azure Developer CLI for deployment
Platforms: Azure · LocalClients: GitHub Copilot · Claude · Any MCP client

Reviewed 2026-08-11

Topics

agentaiapiazdazd-templatesazuree2ejavascriptlangchain-jsmcpmicroservicesmodel-context-protocolopen-apiserverlesstypescript
Stars
197★
Forks
94
Language
TypeScript
License
MIT
Created
2025-07-07
Last push
2026-07-08