China Railway (12306) MCP server

This server implements the Model Context Protocol (MCP), which standardizes the communication between LLMs and external systems. It enables the integration of contextual information with language models, allowing for more tailored and accurate responses.

Installation

Prerequisites

• Go 1.21 or above

Building from Source

Clone the repository and build the binary:

git clone https://github.com/yourusername/12306-mcp-server.git
cd 12306-mcp-server
go build -o mcpserver

Usage

Starting the Server

To start the MCP server with default settings:

./mcpserver

Configuration

The server can be configured using command-line flags:

./mcpserver --host 127.0.0.1 --port 8080

Common configuration options:

• --host: Host address to bind (default: 0.0.0.0)
• --port: Port to listen on (default: 8080)
• --loglevel: Logging level (default: info)

API Endpoints

The server exposes the following endpoints:

• POST /v1/query: Send queries to the model with context
• GET /v1/status: Check server status and health
• GET /v1/models: List available models

Example: Querying the Model

To query the model with context:

curl -X POST http://localhost:8080/v1/query \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {"role": "user", "content": "What train goes from Beijing to Shanghai?"}
    ],
    "context": {
      "format": "json",
      "data": {
        "trains": [
          {"number": "G1", "departure": "Beijing", "arrival": "Shanghai", "duration": "4h28m"},
          {"number": "G5", "departure": "Beijing", "arrival": "Shanghai", "duration": "4h38m"}
        ]
      }
    }
  }'

Integrating with LLM Applications

To use this MCP server with your LLM applications, configure your client to point to the server's endpoint. For example:

import requests

response = requests.post(
    "http://localhost:8080/v1/query",
    json={
        "model": "gpt-3.5-turbo",
        "messages": [{"role": "user", "content": "Find me the fastest train to Shanghai"}],
        "context": {
            "format": "json",
            "data": {"current_location": "Beijing"}
        }
    }
)

print(response.json())

Troubleshooting

Common Issues

• Connection refused: Ensure the server is running and the port is not blocked by a firewall
• Authentication errors: If you've configured authentication, check your API keys
• Timeout errors: For large context processing, consider increasing the timeout settings

Logs

To get more detailed logs, start the server with increased verbosity:

./mcpserver --loglevel debug

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "chinarailway" '{"command":"npx","args":["-y","mcp-server-chinarailway"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "chinarailway": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-server-chinarailway"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "chinarailway": {
            "command": "npx",
            "args": [
                "-y",
                "mcp-server-chinarailway"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect