Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for 12306 train ticket search
12306-mcp wraps 12306 ticket search behind an MCP server so an agent can query travel options from its tool layer. It supports ticket lookup, train filtering, passing-station queries, and transfer searches. The README shows stdio, HTTP, and Docker ways to run it.

Builders who want an MCP-capable agent to search 12306 train tickets and related routes.
You can ask your agent to look up train tickets and route options without leaving your workflow.
What it does
Ticket search
Searches 12306 ticket availability and trip information through the MCP interface.
Train filtering
Lets the agent filter train results after searching.
Passing-station lookup
Supports queries for trains that pass through a given station.
Transfer search
Finds transfer routes for 12306 trips.
stdio and HTTP runtime
Runs as a local MCP server over stdio or on a port with `--port`.
How to get it
- 1Run
git clone https://github.com/Joooook/12306-mcp.git npm i
- 2Run
npx -y 12306-mcp
- 3Run
npx -y 12306-mcp --port [端口号]
- 4Run
docker build . -t 12306-mcp docker run --rm -it 12306-mcp npx 12306-mcp
- 5Run
docker build . -t 12306-mcp docker run -p [your_port]:8080 -d 12306-mcp npx 12306-mcp --port 8080
README
12306-mcp
A 12306 ticket search server based on the Model Context Protocol (MCP). The server provides a simple API interface that allows users to search for 12306 tickets.
基于 Model Context Protocol (MCP) 的12306购票搜索服务器。提供了简单的API接口,允许大模型利用接口搜索12306购票信息。
如需Skill -> https://github.com/Joooook/12306-skill
🚩Features
| 功能描述 | 状态 |
|---|---|
| 查询12306购票信息 | ✅ 已完成 |
| 过滤列车信息 | ✅ 已完成 |
| 过站查询 | ✅ 已完成 |
| 中转查询 | ✅ 已完成 |
| 其余接口,欢迎提feature | 🚧 计划内 |
⚙️Installation
git clone https://github.com/Joooook/12306-mcp.git
npm i
▶️Quick Start
CLI-stdio
npx -y 12306-mcp
CLI-http
npx -y 12306-mcp --port [端口号]
Runtime requirements
The server requires Node.js 18 or newer. The npm run debug command uses
MCP Inspector 2.0.0, which requires Node.js 22.19.0 or newer.
MCP sever configuration
{
"mcpServers": {
"12306-mcp": {
"command": "npx",
"args": [
"-y",
"12306-mcp"
]
}
}
}
Docker-stdio
docker build . -t 12306-mcp
docker run --rm -it 12306-mcp npx 12306-mcp
Docker-http
docker build . -t 12306-mcp
docker run -p [your_port]:8080 -d 12306-mcp npx 12306-mcp --port 8080
📚Documentation
👉️Reference
💭Murmurs
本项目仅用于学习,欢迎催更。
🎫Badges
☕️Donate
请我喝杯奶茶吧。
Files in the repo
- .github
- build
- docs
- src
- .gitignore
- .prettierrc
- Dockerfile
- glama.json
- LICENSE
- package-lock.json
- package.json
- README.md
- tsconfig.json
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
x64dbg-MCP Server is a native MCP (Model Context Protocol) plugin for x64dbg that exposes the debugger's full functionality over HTTP. Connect any MCP-compatible AI assistant and control x64dbg programmatically: set breakpoints, step through code, read memory, dump registers, and more. Built with Zig — zero dependencies, single-binary output, cros

