Second Opinion (Code Assistant)

🚀 Second Opinion MCP Server

An MCP server that combines various AI technologies to provide programming problem solutions. It integrates the following features:

• Insights from Google Gemini AI
• Best practice answers from Stack Overflow
• Analytical results from Perplexity AI

✨ Features

• Offer detailed problem solutions by integrating multi-source context information.
• Automatically detect file languages (via file extensions).
• Extract and format code snippets.
• Automatically generate Markdown-formatted solution reports.
• Collect Git-aware file context.

📦 Installation

1. Create a Configuration File

Create a new config.ts file in the project root directory with the following content:

export const CONFIG = {
  AI_API_KEY: 'your_api_key_here', // Replace with your API key
  STACK_OVERFLOW_API_KEY: 'your_stack_overflow_key_here' // Replace with your Stack Overflow API key
};

2. Install Dependencies

Install the required packages using npm or yarn:

npm install @types/node @types/express express axios

3. Start the Server

Execute the following command to start the MCP server:

node index.ts

💻 Usage Examples

Function Overview

The server provides the following core functions:

1. Multi-source Answers: Integrate results from Gemini AI, Stack Overflow, and Perplexity AI to generate more comprehensive solutions.
2. Language Detection: Automatically identify file languages and provide corresponding support (e.g., JavaScript, Python, etc.).
3. Code Processing: Extract and format code snippets for easy display and analysis.

Request Example

Example Input

{
  "query": "How to implement asynchronous communication in Node.js",
  "file_path": "src/server.ts"
}

Example Output

## Solution Overview

For the question "How to implement asynchronous communication in Node.js", here is a step-by-step solution:

### Step 1: Use the built-in modules `async` or `await`
Node.js provides powerful async/await features to handle asynchronous operations. You can directly use these features to implement asynchronous communication.

#### Example Code
```javascript
const fs = require('fs');

// Asynchronously read file content
async function readFileAsync(filePath) {
  try {
    const data = await fs.promises.readFile(filePath, 'utf8');
    console.log(data);
  } catch (error) {
    console.error('Failed to read file:', error);
  }
}

readFileAsync('src/server.ts');

Step 2: Leverage third-party libraries for advanced asynchronous processing

If you need more complex asynchronous operations, you can consider using third-party libraries such as rxjs or bluebird.

Example Code

const { Observable } = require('rxjs');

// Implement asynchronous communication using RxJS
Observable.fromEventPattern(document, 'click')
  .subscribe(() => {
    console.log('The page was clicked');
  });

Best Practices

1. Error Handling: Always use try-catch blocks inside async functions.
2. Logging: It is recommended to integrate a professional logging system (e.g., Winston) to better track asynchronous operations.
3. Performance Optimization: Avoid unnecessary nesting and keep the code concise.

## 📚 Documentation
### Project Structure

src/ ├── config.ts # Configuration file and API settings ├── fileUtils.ts # File operations and language detection logic ├── index.ts # Application entry point ├── perplexity.ts # Integration implementation of Perplexity AI ├── server.ts # Main logic of the MCP server ├── stackOverflow.ts # Call interface for the Stack Overflow API └── types.ts # TypeScript type definition file

### Known Issues
Refer to [errors.md](./errors.md) for currently known issues and solutions.

> ⚠️ **Important Note**
> 
> Before using the server, ensure that you have correctly configured all necessary API keys and that your network environment allows access to the relevant AI services.