AI Pair Programmer

Ruby-based MCP server offering AI-assisted pair programming tools for review, brainstorming, performance, and security analyses.

other

3

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "k4sku-ai-pair-programmer-mcp": {
      "command": "ruby",
      "args": [
        "./server.rb"
      ],
      "env": {
        "MCP_TIMEOUT": "10000",
        "OPENROUTER_API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

You run a Ruby-based MCP server that provides AI-powered tools for code review, brainstorming, performance analysis, and security review. It runs locally and exposes its functionality to MCP clients via STDIO, streamlining collaboration and code quality activities across your projects.

How to use

Connect to the AI Pair Programmer MCP server from your MCP client. You will access five distinct AI-powered tools through conversations and prompts: pair for general collaboration, review for code feedback, brainstorm for ideation, review_performance for performance suggestions, and review_security for security-focused checks. When you start a session, direct your requests to the tool you want to use and describe the task; the server will provide actionable guidance, optimization ideas, and security recommendations while keeping the conversation context intact.

How to install

Prerequisites you need before installing: a Ruby 3.0+ runtime and an OpenRouter API key. You will install and run the server locally; it is designed to automatically install missing gems on first run and to operate over STDIO for MCP clients.

export OPENROUTER_API_KEY="your_api_key_here"
ruby ./server.rb

Additional sections

Configuration details and troubleshooting help are provided below to ensure you can tailor the server to your environment and resolve common start-time issues.

Models supported by the server include Gemini (default), O3, Grok, DeepSeek, and Claude Opus. You can select an AI model when configuring the client or runtime, depending on available OpenRouter options.

If you encounter a startup timeout when launching, increase the allowed timeout by setting MCP_TIMEOUT to a higher value (for example, 10000 for ten seconds) or start the MCP server in the terminal first to complete the bundling process.

Available tools

pair

General collaboration and problem-solving tool that helps you brainstorm, reason through problems, and plan solutions with AI guidance.

review

Comprehensive code review tool that provides actionable feedback on code quality, style, and potential issues.

brainstorm

Creative ideation tool for exploring new approaches, architectures, and features.

review_performance

Performance analysis tool that suggests bottlenecks, optimizations, and scalable improvements.

review_security

Security-focused review tool that detects vulnerabilities and recommends mitigations.