Mianshiyaserver

🚀 Interview Duck MCP Server

Interview Duck's MCP Server provides a seamless way for intelligent assistants to access interview questions.

🚀 Quick Start

The Interview Duck MCP server is mainly accessed through the Java SDK.

✨ Features

The question search API of Interview Duck is now compatible with the MCP protocol, making it the first interview practice platform in China to support the MCP protocol. For detailed information about the MCP protocol, please refer to the official documentation.

This service is developed based on the MCP Java SDK, and any intelligent assistant that supports the MCP protocol (such as Claude, Cursor, and Qianfan AppBuilder) can easily connect to it.

Tool List

Question Search questionSearch

• Function: Convert interview questions into links to questions on Interview Duck.
• Input: Question
• Output: [Question](Link)

📦 Installation

Prerequisites

A Java 17 runtime environment is required.

Clone the Repository

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

Build the Project

cd mcp-mianshiya-server
mvn clean package

💻 Usage Examples

Basic Usage

Configure Cherry Studio

1. Open the Settings in Cherry Studio and click MCP Server.

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

{
  "mcpServers": {
    "mianshiyaServer": {
      "command": "java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-Dspring.main.web-application-type=none",
        "-Dlogging.pattern.console=",
        "-jar",
        "/yourPath/mcp-server-0.0.1-SNAPSHOT.jar"
      ],
      "env": {}
    }
  }
}

3. Select a model in Settings - Model Service, enter the API key, configure the model parameters, and enable the tool function call feature.

4. Check the box to enable the MCP service below the input box.

5. After the configuration is complete, query interview questions.

Advanced Usage

Code Invocation

1. Add Dependencies

<dependency>
    <groupId>com.alibaba.cloud.ai</groupId>
    <artifactId>spring-ai-alibaba-starter</artifactId>
    <version>1.0.0-M6.1</version>
</dependency>
<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-mcp-client-spring-boot-starter</artifactId>
    <version>1.0.0-M6</version>
</dependency>

2. Configure the MCP Server You need to configure the relevant parameters of the MCP server in application.yml:

spring:
  ai:
    mcp:
      client:
        stdio:
          # Specify the MCP server configuration file
          servers-configuration: classpath:/mcp-servers-config.json
  mandatory-file-encoding: UTF-8

The configuration of mcp-servers-config.json is as follows:

{
  "mcpServers": {
    "mianshiyaServer": {
      "command": "java",
      "args": [
        "-Dspring.ai.mcp.server.stdio=true",
        "-Dspring.main.web-application-type=none",
        "-Dlogging.pattern.console=",
        "-jar",
        "/Users/gulihua/Documents/mcp-server/target/mcp-server-0.0.1-SNAPSHOT.jar"
      ],
      "env": {}
    }
  }
}

We use Alibaba's Tongyi Qianwen model as the client, so we introduce the spring-ai-alibaba-starter dependency. If you need other models, please adjust according to the specific situation.

3. Initialize the Chat Client

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

4. Interface Invocation

@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]"));
}