Azure AI Travel Agents
A robust enterprise application sample (deployed on ACA) that leverages MCP and multiple AI agents orchestrated by Langchain.js, Llamaindex.TS and Microsoft Agent Framework.
What is Azure AI Travel Agents?
Azure AI Travel Agents is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to robust enterprise application sample (deployed on aca) that leverages mcp and multiple ai agents orchestrated by langchain.js, llamaindex.ts and microsoft agent framework.
A robust enterprise application sample (deployed on ACA) that leverages MCP and multiple AI agents orchestrated by Langchain.js, Llamaindex.TS and Microsoft Agent Framework.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A robust enterprise application sample (deployed on ACA) tha
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx azure-ai-travel-agentsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Azure AI Travel Agents
Azure AI Travel Agents is a reference enterprise application that demonstrates how to build multi-agent AI systems using MCP as the inter-agent communication protocol. It deploys four specialised agents — customer query understanding, destination recommendation, itinerary planning, and an echo MCP example — orchestrated by your choice of LangChain.js, LlamaIndex.TS, or Microsoft Agent Framework. The entire application runs on Azure Container Apps using the Phi4 14B model via Docker Model Runner, with OpenTelemetry tracing via an Aspire dashboard. Teams use it as a production-grade starting point for building AI-powered enterprise travel or booking platforms on Azure.
Prerequisites
- Git installed for cloning the repository
- Node.js 22 or later (for UI and API services)
- Docker and Docker Compose installed (for MCP servers and the Docker Model Runner)
- Azure CLI and Azure Developer CLI (azd) installed and authenticated if deploying to Azure
- 16 GB RAM minimum recommended for running the Phi4 14B model locally
Clone the repository
Clone the Azure-Samples repository to your local machine.
git clone https://github.com/Azure-Samples/azure-ai-travel-agents.git
cd azure-ai-travel-agentsRun the automated setup script
Execute the official preview setup script for your platform. On Linux/macOS use the bash one-liner; on Windows use the PowerShell equivalent.
# Linux/macOS:
/bin/bash <(curl -fsSL https://aka.ms/azure-ai-travel-agents-preview)
# Windows PowerShell 7+:
iex "& { $(irm https://aka.ms/azure-ai-travel-agents-preview-win) }"Configure environment variables
The setup script auto-generates .env files. For Azure deployments, set the target region — swedencentral is the default because it has the required OpenAI model availability.
# Example .env override:
AZURE_LOCATION=swedencentralStart services locally with Docker
Use Docker Compose to start the MCP servers and model runner locally before deploying to Azure.
docker compose up -dDeploy to Azure Container Apps
Log in with the Azure Developer CLI and run 'azd up' to provision all Azure resources and deploy the containerised services.
azd auth login
azd upVerify via the web chat interface
Open the deployed web URL and submit a travel query in the chat interface. The agents will coordinate via MCP and return a structured recommendation.
Azure AI Travel Agents Examples
Client configuration
MCP server config referencing the echo-ping agent as an example MCP server endpoint (replace with your deployed URL).
{
"mcpServers": {
"azure-travel-agents": {
"command": "npx",
"args": ["azure-ai-travel-agents"]
}
}
}Prompts to try
Example queries to send through the web chat interface to exercise the multi-agent pipeline.
- "I want a 10-day trip to Japan in spring. I love hiking and local food."
- "Recommend beach destinations in Europe for a family of four in August."
- "Create a detailed day-by-day itinerary for a business trip to Singapore."
- "What are the best cities for a solo traveller interested in history and architecture?"Troubleshooting Azure AI Travel Agents
Docker Model Runner fails to start the Phi4 14B model
The Phi4 14B model requires approximately 7.8 GB of VRAM or RAM. Ensure Docker has access to at least 16 GB of system memory and that the Docker runtime has GPU passthrough configured if available.
azd up fails with a quota error in the selected Azure region
Set AZURE_LOCATION to a different region that supports the required OpenAI model (swedencentral is recommended). Run 'azd env set AZURE_LOCATION swedencentral' before retrying 'azd up'.
The web chat returns no response from the agents
Check the Aspire dashboard for OpenTelemetry traces — it shows which agent failed and why. Common causes include missing environment variables or container startup timeouts. Run 'docker compose logs' for local debugging.
Frequently Asked Questions about Azure AI Travel Agents
What is Azure AI Travel Agents?
Azure AI Travel Agents is a Model Context Protocol (MCP) server that robust enterprise application sample (deployed on aca) that leverages mcp and multiple ai agents orchestrated by langchain.js, llamaindex.ts and microsoft agent framework. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Azure AI Travel Agents?
Follow the installation instructions on the Azure AI Travel Agents GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Azure AI Travel Agents?
Azure AI Travel Agents works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Azure AI Travel Agents free to use?
Yes, Azure AI Travel Agents is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Azure AI Travel Agents Alternatives — Similar Business Applications Servers
Looking for alternatives to Azure AI Travel Agents? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Azure AI Travel Agents in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Azure AI Travel Agents?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.