MCP Catalogs
← Homemcp-agent-langchainjs screenshot

mcp-agent-langchainjs

by Azure-Samples·★ 183·Score 48

A burger ordering AI agent system using LangChain.js and MCP servers to interact with a restaurant API.

ai-llmecommercedeveloper-tools
92
Forks
2
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

This project demonstrates how to build AI agents that interact with real-world APIs using the Model Context Protocol (MCP). It features a complete burger ordering system with a serverless API, web interfaces, and an MCP server that enables AI agents to browse menus, place orders, and track order status. The system uses LangChain.js for LLM reasoning and tool calling, built with Azure services including Static Web Apps, Azure Functions, and Cosmos DB.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:AI-powered food ordering system through natural language conversation
you:Demonstration of MCP tool calling for real-world applications
you:Serverless architecture for scalable AI agents
you:What MCP servers are included in this project?
you:Can I test this application without cloud costs?

When to choose this

Teams looking to build production-ready MCP servers for e-commerce scenarios, especially those already using Azure serverless infrastructure.

When NOT to choose this

For non-Azure environments or if you need a simpler MCP implementation without the complexity of a full multi-service architecture.

Tools this server exposes

3 tools extracted from the README
  • view_menu

    View the burger menu and available items

  • place_order

    Place a new burger order with specific items and preferences

  • get_order_status

    Check the current status of an existing order

Note: The table was truncated in the README, but I could see the beginning of an MCP tools section with three burger-related tools. Tool names were visible but descriptions and signatures were not fully shown.

Comparable tools

langchain-mcpopenai-mcpbrowser-mcp

Installation

Installation Steps

  1. **GitHub Codespaces (Recommended)**:

- Open the project in [GitHub Codespaces](https://codespaces.new/Azure-Samples/mcp-agent-langchainjs?hide_repo_select=true&ref=main&quickstart=true) for a preconfigured environment

  1. **Local Development**:

- Clone the repository: git clone <your-repo-url> - Install Node.js LTS - Install Azure Developer CLI 1.19+ - For local testing with Ollama: ``bash ollama pull qwen3:8b ` Create a .env file with: `env AZURE_OPENAI_API_ENDPOINT="http://localhost:11434/v1" AZURE_OPENAI_MODEL="qwen3:8b" AZURE_OPENAI_API_KEY="__not_used__" `` - Start the application following the README instructions

  1. **Deployment to Azure**:

- Run azd auth login - Run azd up to deploy all services

**Claude Desktop Configuration** (add to claude_desktop_config.json):

{
  "mcpServers": {
    "burger-mcp": {
      "command": "node",
      "args": ["packages/burger-mcp/dist/server.js"]
    }
  }
}

FAQ

What MCP servers are included in this project?
The project includes a burger MCP server (for ordering burgers) and a beer MCP server (for AI-powered beer recommendations).
Can I test this application without cloud costs?
Yes, the application can be tested locally using Ollama models without any cloud costs.

Compare mcp-agent-langchainjs with

mcp-agent-langchainjs vs ultimate_mcp_servermcp-agent-langchainjs vs mcp-server-chartmcp-agent-langchainjs vs everythingmcp-agent-langchainjs vs filesystemmcp-agent-langchainjs vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.