Second Opinion

Second Opinion

Provides AI-powered assistance for coding problems using Google's Gemini AI, combined with Perplexity insights and Stack Overflow references, facilitating contextual analysis and automatic response archiving for improved troubleshooting.

PoliTwit1984

Remote Shell Execution
Web Automation & Stealth
Git Management Tools
Data & App Analysis
Visit Server

README

Second Opinion MCP Server

An MCP server that provides AI-powered assistance for coding problems by combining insights from:

  • Google's Gemini AI
  • Stack Overflow accepted answers
  • Perplexity AI analysis

Features

  • Get detailed solutions for coding problems with context from multiple sources
  • Automatic language detection from file extensions
  • Code snippet extraction and formatting
  • Markdown report generation for solutions
  • Git-aware file context gathering

Setup

  1. Install dependencies:
npm install
  1. Build the server:
npm run build
  1. Configure environment variables in MCP settings:
{
  "mcpServers": {
    "second-opinion": {
      "command": "node",
      "args": ["/path/to/second-opinion-server/build/index.js"],
      "env": {
        "GEMINI_API_KEY": "your-gemini-api-key",
        "PERPLEXITY_API_KEY": "your-perplexity-api-key",
        "STACK_EXCHANGE_KEY": "your-stack-exchange-key"
      }
    }
  }
}

Required environment variables:

  • GEMINI_API_KEY: Google's Gemini AI API key
  • PERPLEXITY_API_KEY: Perplexity AI API key
  • STACK_EXCHANGE_KEY: Stack Exchange API key (optional, uses anonymous access if not provided)

Usage

The server provides a single tool:

get_second_opinion

Get AI-powered insights and solutions for coding problems.

Input Schema:

{
  "goal": "string (required) - What you're trying to accomplish",
  "error": "string (optional) - Any error messages you're seeing",
  "code": "string (optional) - Relevant code context",
  "solutionsTried": "string (optional) - What solutions you've already tried",
  "filePath": "string (optional) - Path to the file with the issue"
}

Example Input:

{
  "goal": "Fix React useEffect cleanup error",
  "error": "React Hook useEffect has a missing dependency: 'socket'. Either include it in the dependency array, or remove the dependency array  react-hooks/exhaustive-deps",
  "code": "useEffect(() => {\n  socket.on('message', handleMessage);\n  return () => socket.off('message');\n}, []);",
  "solutionsTried": "I tried adding socket to the dependency array but then it causes infinite re-renders"
}

Example Response:

Understanding the Problem

The core issue lies in how React's useEffect hook manages side effects and their dependencies. When you provide an empty dependency array ([]), you're telling React that the effect should only run once when the component mounts and that the cleanup function should run when the component unmounts.

However, in your code, the socket object is used within the effect. This creates a closure where the handleMessage function and the cleanup function (socket.off('message')) implicitly depend on the current value of socket. If socket ever changes (e.g., due to a reconnection or reinitialization), your effect will be using an outdated socket instance.

Common Issues

  • Stale Closures: The event handler (handleMessage) might be working with an old socket object
  • Incorrect Cleanup: The socket.off('message') might not remove the intended event listener
  • Memory Leaks: Failed cleanup can lead to memory leaks and unexpected behavior

Solutions

1. Using useRef for Stable References

import React, { useEffect, useRef } from 'react';

function MyComponent({ socket }) {
  const socketRef = useRef(socket);

  useEffect(() => {
    const currentSocket = socketRef.current;
    currentSocket.on('message', handleMessage);
    return () => {
      currentSocket.off('message');
    };
  }, []); // Empty dependency array is now safe
}

Why This Works:

  • useRef creates a mutable object that persists across renders
  • The ref object itself doesn't change, preventing effect re-runs
  • You can access the latest socket value via the ref

2. Using useCallback for Handlers

import React, { useEffect, useRef, useCallback } from 'react';

function MyComponent({ socket, someProp }) {
  const socketRef = useRef(socket);

  const handleMessage = useCallback((message) => {
    // Do something with the message and potentially someProp
    console.log(message, someProp);
  }, [someProp]); // Include dependencies of handleMessage

  useEffect(() => {
    const currentSocket = socketRef.current;
    currentSocket.on('message', handleMessage);
    return () => {
      currentSocket.off('message', handleMessage);
    };
  }, [handleMessage]); // Depend on the memoized handler
}

3. Managing Socket Lifecycle Inside useEffect

import React, { useEffect, useState } from 'react';

function MyComponent() {
  const [messages, setMessages] = useState([]);

  useEffect(() => {
    const socket = new WebSocket('your_websocket_url');

    const handleMessage = (message) => {
      setMessages((prevMessages) => [...prevMessages, message]);
    };

    socket.on('message', handleMessage);

    return () => {
      socket.off('message', handleMessage);
      socket.close();
    };
  }, []); // Empty array is correct - socket lifecycle managed within
}

4. Custom Hook Solution

function useSocket(url) {
  const [messages, setMessages] = useState([]);
  const socketRef = useRef(null);

  useEffect(() => {
    const socket = new WebSocket(url);
    socketRef.current = socket;

    const handleMessage = (message) => {
      setMessages((prevMessages) => [...prevMessages, message]);
    };

    socket.on('message', handleMessage);

    return () => {
      socket.off('message', handleMessage);
      socket.close();
    };
  }, [url]);

  const sendMessage = useCallback((message) => {
    if (socketRef.current?.readyState === WebSocket.OPEN) {
      socketRef.current.send(message);
    }
  }, []);

  return { messages, sendMessage };
}

Best Practices

  1. Dependency Management

    • Use useRef for stable references
    • Memoize handlers with useCallback
    • Consider socket lifecycle management
  2. Performance Optimization

    • Minimize unnecessary re-renders
    • Handle high-volume messages efficiently
    • Use appropriate cleanup patterns
  3. Error Handling

    • Handle connection errors gracefully
    • Implement reconnection logic if needed
    • Clean up resources properly
  4. Testing Considerations

    • Mock WebSocket connections in tests
    • Verify event listener cleanup
    • Test error scenarios

Project Structure

src/
├── config.ts        # Configuration and API settings
├── fileUtils.ts     # File operations and language detection
├── index.ts         # Entry point
├── perplexity.ts   # Perplexity AI integration
├── server.ts       # MCP server implementation
├── stackOverflow.ts # Stack Overflow API integration
└── types.ts        # TypeScript interfaces

Known Issues

See errors.md for current issues and workarounds.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Mult Fetch MCP Server

Mult Fetch MCP Server

A versatile MCP-compliant web content fetching tool that supports multiple modes (browser/node), formats (HTML/JSON/Markdown/Text), and intelligent proxy detection, with bilingual interface (English/Chinese).

Featured
Local
AIO-MCP Server

AIO-MCP Server

🚀 All-in-one MCP server with AI search, RAG, and multi-service integrations (GitLab/Jira/Confluence/YouTube) for AI-enhanced development workflows. Folk from

Featured
Local
Hyperbrowser MCP Server

Hyperbrowser MCP Server

Welcome to Hyperbrowser, the Internet for AI. Hyperbrowser is the next-generation platform empowering AI agents and enabling effortless, scalable browser automation. Built specifically for AI developers, it eliminates the headaches of local infrastructure and performance bottlenecks, allowing you to

Featured
Local
React MCP

React MCP

react-mcp integrates with Claude Desktop, enabling the creation and modification of React apps based on user prompts

Featured
Local
Any OpenAI Compatible API Integrations

Any OpenAI Compatible API Integrations

Integrate Claude with Any OpenAI SDK Compatible Chat Completion API - OpenAI, Perplexity, Groq, xAI, PyroPrompts and more.

Featured
Exa MCP

Exa MCP

A Model Context Protocol server that enables AI assistants like Claude to perform real-time web searches using the Exa AI Search API in a safe and controlled manner.

Featured
BigQuery

BigQuery

This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data! Think of it as a friendly translator that sits between your AI assistant and your database, making sure they can chat securely and efficiently.

Featured