azure-ai-travel-agents

Name: azure-ai-travel-agents
Rating: 87 (1 reviews)
Author: Azure-Samples

MCP Server

Azure-Samples/azure-ai-travel-agents

This repository provides a modular multi-agent travel planning system with three standalone orchestration options: LangChain.js, LlamaIndex.TS, and the Microsoft Agent Framework. It uses Model Context Protocol (MCP) microservices to coordinate specialized agents for customer queries, destination recommendations, and itinerary planning.

476 183MITUpdated 2026-08-12

Great

View on GitHub Open source file

Overview

The Azure AI Travel Agents project demonstrates a flexible architecture for building multi-agent AI systems by decoupling orchestration layers from tool implementations. It features three distinct orchestration runtimes—LangChain.js (Node.js/TypeScript), LlamaIndex.TS (Node.js/TypeScript), and Microsoft Agent Framework (Python)—all communicating with a shared set of MCP microservices written in .NET, Java, Python, and TypeScript. A unified Angular frontend interacts with these backends, while Bicep templates facilitate deployment to Azure Container Apps.

Capabilities

▸Multi-agent orchestration via supervisor and triage patterns
▸Model Context Protocol (MCP) tool integration
▸Polyglot microservice architecture (.NET, Java, Python, TypeScript)
▸Real-time response streaming
▸Angular frontend UI integration
▸Infrastructure as Code via Azure Bicep

Best for

Orchestrating multi-agent systems using LangChain, LlamaIndex, or Microsoft Agent Framework, Integrating Model Context Protocol (MCP) tool servers across polyglot microservices, Developing end-to-end travel assistant applications with customer query handling and itinerary generation, Comparing different AI orchestration frameworks within a uniform architecture

Works with

CodexGitHub CopilotClaude CodeCursor

Evoa Score breakdown= Σ (score × weight)

Task usefulness20%100 → +20.0

実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析

Code quality15%90 → +13.5

実装・指示の品質。 — AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ

Documentation12%58 → +7.0

ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量

Security15%80 → +12.0

危険・不審な挙動が無いか。 — AIによるセキュリティレビュー

Originality10%85 → +8.5

ありふれたラッパーではない独自性。 — AIによる独自性判定

Popularity8%73 → +5.8

コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）

Compatibility5%100 → +5.0

対応AIエージェントの広さ。 — AIによる対応エージェント判定

Weighted total86.8 / 100

ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。ランキングはこのScoreのみで決まり、広告で変わりません。算出方法の詳細 →

Security considerations

Ensure proper credential management when connecting to Azure OpenAI or third-party LLM providers. MCP servers communicate over local ports, requiring network security configuration in production deployments.