MCP Mianshiya Server

🚀 Interview Duck MCP Server

Interview Duck's question search API now supports the MCP protocol, making it the first online question - practicing platform in China to be compatible with the MCP protocol. For detailed information about the MCP protocol, please refer to the MCP official documentation.

This project is developed based on the MCP Java SDK. Any intelligent assistant that supports the MCP protocol (such as Claude, Cursor, and Qianfan AppBuilder) can be easily integrated.

The following provides detailed adaptation instructions.

✨ Features

Tool List

Question Search questionSearch

• Function: Retrieve interview questions and return links to the corresponding questions on Interview Duck.
• Input format: Question
• Output format: [Question](Link)

🚀 Quick Start

Using the Interview Duck MCP Server is mainly achieved through the Java SDK.

Java Integration

⚠️ Important Note

A Java 17 runtime environment is required.

📦 Installation

git clone https://github.com/yuyuanweb/mcp-mianshiya-server

Build

cd mcp-mianshiya-server
mvn clean package

Usage Steps

1. Open the Settings in Cherry Studio and select the MCP Server option.

2. Click Edit JSON and add the following content to the configuration file:

{
  "mcpServers": {
    "mianshiyaServer": {
      "command": "java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-Dspring.main.web-application-type=none",
        "-Dlogging.pattern.console=",
        "yyyy-MM-dd HH:mm:ssSlf4j SimpleDateFormat"
      ],
      "environment": [],
      "workingDirectory": "."
    }
  }
}

3. Initialize the chat client:

@Bean
public ChatClient initChatClient(ChatClient.Builder chatClientBuilder,
                                 ToolCallbackProvider mcpTools) {
    return chatClientBuilder
        .defaultTools(mcpTools)
        .build();
}

4. Interface call example:

@PostMapping(value = "/ai/answer/sse", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<String> generateStreamAsString(@RequestBody AskRequest request) {

    Flux<String> content = chatClient.prompt()
            .user(request.getContent())
            .stream()
            .content();
    return content
            .concatWith(Flux.just("[complete]"));
}

📚 Documentation

Notes

1. The translated code examples maintain the original format and comments to ensure readability and accuracy.
2. The image paths and reference methods remain unchanged to avoid affecting actual use.
3. Terminology and professional vocabulary are presented using the standard expressions in technical documentation.