Second Opinion MCP Server
An AI-powered coding assistant that combines insights from Gemini, Stack Overflow, and Perplexity AI to help solve programming problems.
🧠 Second Opinion MCP Server
Stuck on a problem? Get a second opinion from a different model.
An MCP server that combines Gemini, Perplexity, and Stack Overflow to give Claude (or any MCP client) a multi-source second take on tough coding problems.
Why
When Claude gets stuck — or just confidently wrong — the fastest unblocker is a different model with different training. This server makes that one tool call away:
- 🟦 Google Gemini for an alternative model perspective
- 🟪 Perplexity for fresh web-grounded analysis
- 🟧 Stack Overflow for accepted answers from real engineers
You stay in your Claude conversation. The second opinion comes to you.
Features
- 🌐 Multi-source synthesis — combines insights from three different sources into one answer
- 🔤 Automatic language detection from file extensions
- 📋 Code snippet extraction and clean formatting
- 📄 Markdown report generation for solutions
- 🧠 Git-aware context gathering — includes nearby files when relevant
- ⚡ Single tool call — no need to context-switch between chat apps
Install
git clone https://github.com/joewilsonai/second-opinion-mcp-server
cd second-opinion-mcp-server
npm install
npm run build
Configure in Claude Desktop
Edit your claude_desktop_config.json:
{
"mcpServers": {
"second-opinion": {
"command": "node",
"args": ["/absolute/path/to/second-opinion-mcp-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"
}
}
}
}
Restart Claude Desktop.
Required environment variables
| Variable | Source | Notes |
|---|---|---|
GEMINI_API_KEY | aistudio.google.com | Required |
PERPLEXITY_API_KEY | perplexity.ai/settings/api | Required |
STACK_EXCHANGE_KEY | stackapps.com/apps/oauth/register | Optional — falls back to anonymous |
Usage
Once installed, just ask Claude:
"Get a second opinion on this race condition I'm hitting in our worker pool."
Claude will call the tool, pass your code + context, and synthesize a response from all three sources.
Stack
- TypeScript + Node.js 18+
- @modelcontextprotocol/sdk
- @google/generative-ai (Gemini)
- Perplexity API
- Stack Exchange API
Related MCP servers
- 🔍 mcp-perplexity-server (⭐ 14) — Perplexity-only, lighter weight
- 🐙 github-meta-mcp-server — Natural-language GitHub repo management
License
MIT
İlgili Sunucular
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MATLAB
Execute MATLAB scripts and functions via MCP clients. Requires a local MATLAB installation.
MCP Servers Collection
A collection of MCP servers for Claude Desktop, providing access to network tools, code linters, and Proxmox virtualization management.
PHP MCP Server
Provides semantic PHP code analysis and refactoring tools, enabling AI assistants to perform safe, intelligent code transformations at the AST level.
Docfork
Provides up-to-date documentation for over 9000 libraries directly within AI code editors.
Merge MCP Server
Integrates the Merge Unified API with any LLM provider using the MCP protocol.
Health Microservice API
A FastAPI microservice for health-related operations, featuring JWT authentication and a PostgreSQL database with Alembic migrations.
Studio MCP
Turns any command-line interface (CLI) command into a simple StdIO-based MCP server.
paytoll-mcp
Access 20+ DeFi, crypto, and AI endpoints through micro-payments. Get Aave rates, build DeFi transactions, fetch crypto prices, resolve ENS names, search Twitter, and query LLMs - all paid per-call with USDC on Base. No API keys needed, payment is the auth
VSCode Maestro MCP
The most comprehensive MCP server for VS Code — 100+ tools across 25 categories. File ops, terminal, git, LSP providers (hover, completion, definition, references), and more. Free core + premium features.
MCP Code Crosscheck
A server for bias-resistant AI code review using cross-model evaluation.