Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/jadenmaciel/ai-validation-mcp-server.git
cd ai-validation-mcp-server
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txtRegister it in Claude Code
claude mcp add ai-validation-mcp -- python3 /path/to/ai-validation-mcp-server/run_mcp_auto.pyReplace any placeholder paths in the command with the real path on your machine.
Make your agent remember this setup
ai-validation-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Fully automatic prompt enhancement using expert engineering techniques
- Visual feedback showing exactly what optimizations were applied
- Automatic detection of technical, creative, or analytical content
- Domain-specific context injection for higher quality responses
Try it
Original README from jadenmaciel/ai-validation-mcp-server
🚀 AI Validation MCP Server - Automatic Prompt Optimization
A fully automatic prompt optimization Model Context Protocol (MCP) server that enhances every prompt with world-class prompt engineering techniques. No manual intervention required - just install, configure, and every prompt gets automatically optimized!
✨ What It Does
🎯 Fully Automatic: Every prompt you send gets automatically enhanced with expert techniques
🧠 Expert-Level Optimization: Applies world-class prompt engineering without any manual work
🔍 Visual Feedback: Shows exactly what optimizations were applied to each prompt
⚡ Smart Detection: Automatically detects technical, creative, or analytical content
🎨 Domain Expertise: Adds appropriate expert context based on your prompt content
🎯 Example: Before vs After
**Your Original Prompt:**
Use the auto_optimize tool with prompt: "How do I write better Python code?"
**What You'll See (Automatically Enhanced):**
🚀 **AI VALIDATION: PROMPT AUTOMATICALLY OPTIMIZED** 🚀
🔧 **ORIGINAL PROMPT**: How do I write better Python code?
✨ **AUTO-OPTIMIZED VERSION**: Please provide a comprehensive and detailed response with specific examples and practical guidance.
As a senior technical expert, please include best practices, potential pitfalls, and real-world implementation considerations.
Please explain your reasoning and methodology.
🔍 **OPTIMIZATIONS APPLIED**:
• 🎯 Enhanced clarity and detail requirements
• 🛠️ Technical expertise context added
• 🧠 Reasoning and methodology requested
• 🌟 Expert system identity applied
---
[Then you get a comprehensive expert response with examples, best practices, step-by-step guidance, etc.]
🚀 Quick Start
**Step 1: Install**
# Clone the repository
git clone https://github.com/jadenmaciel/ai-validation-mcp-server.git
cd ai-validation-mcp-server
# Set up virtual environment
python3 -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
# Install dependencies
pip install -r requirements.txt
**Step 2: Configure Cursor**
Add this to your ~/.cursor/mcp.json file:
{
"mcpServers": {
"ai_validation_auto": {
"command": "python3",
"args": ["/path/to/ai-validation-mcp-server/run_mcp_auto.py"]
}
}
}
Important: Replace /path/to/ai-validation-mcp-server/ with your actual path!
**Step 3: Restart Cursor**
- Close all Cursor windows
- Quit Cursor entirely (Cmd+Q / Ctrl+Q)
- Restart Cursor
**Step 4: Verify It's Working**
- Go to Settings → Features → MCP Servers
- Look for
ai_validation_autowith a green dot ✅ - Try asking any question - you should see the optimization indicators!
🎯 Automatic Optimizations Applied
The server automatically detects your prompt type and applies appropriate enhancements:
**🛠️ Technical Prompts** (code, programming, technical questions)
- Adds senior technical expert context
- Requests best practices and pitfalls
- Asks for implementation considerations
**🎨 Creative Prompts** (writing, design, creative tasks)
- Adds creative professional context
- Requests innovative approaches and options
- Asks for creative insights
**📊 Analytical Prompts** (data, research, analysis)
- Adds analytical expert context
- Requests systematic analysis
- Asks for data-driven insights
**🎯 All Prompts Get:**
- Enhanced clarity and detail requirements
- Structured response formatting (when appropriate)
- Concrete examples and illustrations
- Step-by-step explanations for complex topics
- Expert-level system identity
📁 Project Structure
ai-validation-mcp-server/
├── ai_validation_mcp_auto.py # 🚀 Main automatic optimization server
├── run_mcp_auto.py # 🔧 Server runner with venv handling
├── requirements.txt # 📦 Python dependencies
├── README.md # 📖 This documentation
├── LICENSE # ⚖️ MIT License
├── .gitignore # 🙈 Git ignore rules
└── venv/ # 🐍 Virtual environment (auto-created)
🔧 Configuration Options
The server works automatically with zero configuration, but you can customize by editing ai_validation_mcp_auto.py:
- Modify optimization rules in
optimize_user_prompt() - Adjust expert system prompt in
create_expert_system_prompt() - Change detection patterns for different prompt types
🔍 Troubleshooting
**Green dot not showing?**
Step 1: Ensure MCP Server is Set Up Go to your MCP server folder:
cd /home/jaden/ai-validation-server