Yan Autotravel
AI Travel Planner 是一个基于 Spring Boot + Spring AI 的后端与 Vue 3 + Vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 MCP (Model Context Protocol) 工具链，支持从 自然语言理解 → RAG (Retrieval-Augmented Generation) → 多 Agent 协同 → 个性化生成 的完整 AI 应用流程。同时配套 CSV 向量化预处理脚本，实
What is Yan Autotravel?
Yan Autotravel is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to ai travel planner 是一个基于 spring boot + spring ai 的后端与 vue 3 + vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 mcp (model context protocol) 工具链，支持从 自然语言理解 → rag (retrieval-augmented generation) → ...
AI Travel Planner 是一个基于 Spring Boot + Spring AI 的后端与 Vue 3 + Vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 MCP (Model Context Protocol) 工具链，支持从 自然语言理解 → RAG (Retrieval-Augmented Generation) → 多 Agent 协同 → 个性化生成 的完整 AI 应用流程。同时配套 CSV 向量化预处理脚本，实
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- AI Travel Planner 是一个基于 Spring Boot + Spring AI 的后端与 Vue 3 +
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx yan-autotravelConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Yan Autotravel
Yan AutoTravel is a full-stack AI travel planning application built on Spring Boot and Spring AI with a Vue 3 frontend, integrating MCP tools for real-world data like Amap (高德地图) for route planning and 12306 for Chinese train schedules. It combines a RAG pipeline over vectorized city data with a ReAct multi-agent framework, enabling natural-language itinerary creation, personalized point-of-interest recommendations, and multimodal image analysis for travel context. Developers use it as a reference architecture for building MCP-integrated travel or domain-specific AI agents with Spring AI.
Prerequisites
- Java 17 or higher with Maven
- Node.js 18 or higher and npm (for the Vue 3 frontend)
- Python 3.10+ with pandas, requests, and Pillow (for optional CSV vector ingestion)
- A DashScope (Alibaba Cloud) API key for the Qwen LLM backend
- Amap API credentials and/or 12306 MCP service access for live travel data
Clone the repository
Clone the Yan AutoTravel repository and review the backend and frontend sub-directories.
git clone https://github.com/YongyanLiututu/Yan-AutoTravel-.git
cd Yan-AutoTravel-Configure the backend application
Edit backend/src/main/resources/application.yml to set your DashScope API key, the Qwen model name, and the path to your city data directory. Also set the MCP server endpoints for Amap and 12306.
# application.yml (key fields)
spring.ai.openai.api-key: "your-dashscope-api-key"
spring.ai.openai.base-url: "https://dashscope.aliyuncs.com/compatible-mode/v1"
spring.ai.openai.chat.options.model: "qwen2.5-7b-instruct"
app.citydataDir: "/path/to/citydata"Start the Spring Boot backend
Build and run the backend server. It starts on port 8080 and exposes REST API endpoints for Q&A, itinerary creation, and recommendations.
cd backend
mvn spring-boot:runStart the Vue 3 frontend
Install frontend dependencies and start the Vite dev server on port 5173.
cd web
npm install
npm run devIngest city vector data (optional)
If you have city POI data in CSV format, run the ingestion scripts to vectorize it and load it into the RAG retrieval pipeline.
cd vector-ingest
pip install pandas requests pillow
python ingest_hyper_csv.py
python image_jobs.py ./output/poi_normalized.csvYan Autotravel Examples
Client configuration
If exposing Yan AutoTravel's MCP endpoint to an external AI client, configure it as an SSE server pointing to the Spring Boot backend.
{
"mcpServers": {
"yan-autotravel": {
"type": "sse",
"url": "http://localhost:8080/mcp"
}
}
}Prompts to try
Use these prompts in the Vue 3 frontend chat UI or via the REST API to exercise the AI travel planning features.
- "Plan a 5-day itinerary for Beijing including top historical sites and local food."
- "What train options are available from Shanghai to Hangzhou tomorrow morning?"
- "Recommend restaurants near Wangfujing that are open for dinner."
- "Analyze this photo of a landmark and tell me what it is and nearby attractions."
- "Create a day trip plan from Chengdu with transportation and timing details."Troubleshooting Yan Autotravel
Backend fails to start with 'API key invalid' from DashScope
Ensure your DashScope API key is set correctly in application.yml and that you have quota for the qwen2.5-7b-instruct model. You can obtain a key from https://dashscope.aliyuncs.com/.
Amap route planning returns empty results
Verify the MCP_AMAP_SERVER URL in application.yml is reachable and that your Amap API credentials are valid. The Amap MCP service requires a registered application key from https://console.amap.com/.
Frontend at port 5173 cannot reach the backend
Check that the Spring Boot backend is running on port 8080 and has CORS configured to allow requests from http://localhost:5173. Review the CORS configuration in the Spring Boot WebMvcConfigurer bean.
Frequently Asked Questions about Yan Autotravel
What is Yan Autotravel?
Yan Autotravel is a Model Context Protocol (MCP) server that ai travel planner 是一个基于 spring boot + spring ai 的后端与 vue 3 + vite 的前端组合项目，面向智能旅游场景，提供 智能行程规划、多模态问答与个性化推荐 能力。 系统集成了 mcp (model context protocol) 工具链，支持从 自然语言理解 → rag (retrieval-augmented generation) → 多 agent 协同 → 个性化生成 的完整 ai 应用流程。同时配套 csv 向量化预处理脚本，实 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Yan Autotravel?
Follow the installation instructions on the Yan Autotravel GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Yan Autotravel?
Yan Autotravel works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Yan Autotravel free to use?
Yes, Yan Autotravel is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Yan Autotravel Alternatives — Similar Business Applications Servers
Looking for alternatives to Yan Autotravel? 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 Yan Autotravel 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 Yan Autotravel?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.