Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Prompt Auto-Optimizer MCPstart optimizing a prompt for summarizing research papers"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Prompt Auto-Optimizer MCP
AI-Powered Prompt Evolution - An MCP server that automatically optimizes your AI prompts using evolutionary algorithms.
🎯 Purpose
Automatically evolve and optimize AI prompts to improve performance, creativity, and reliability. Uses genetic algorithms to iteratively improve prompts based on real performance data.
Related MCP server: Vibe Coder MCP
🛠️ Installation
# Clone and install
git clone https://github.com/your-org/prompt-auto-optimizer-mcp.git
cd prompt-auto-optimizer-mcp
npm install
npm run build
# Start the MCP server
npm run mcp:start⚙️ Configuration
Add to your Claude Code settings (.claude/settings.json):
{
"mcp": {
"servers": {
"prompt-optimizer": {
"command": "npx",
"args": ["prompt-auto-optimizer-mcp"],
"cwd": "./path/to/prompt-auto-optimizer-mcp"
}
}
}
}🔧 Available Tools
Core Optimization Tools
gepa_start_evolution
Start optimizing a prompt using evolutionary algorithms.
{
taskDescription: string; // What you want to optimize for
seedPrompt?: string; // Starting prompt (optional)
config?: {
populationSize?: number; // How many variants to test (default: 20)
generations?: number; // How many iterations (default: 10)
mutationRate?: number; // How much to change prompts (default: 0.15)
};
}gepa_evaluate_prompt
Test how well a prompt performs on specific tasks.
{
promptId: string; // Which prompt to test
taskIds: string[]; // What tasks to test it on
rolloutCount?: number; // How many times to test (default: 5)
}gepa_reflect
Analyze why prompts fail and get improvement suggestions.
{
trajectoryIds: string[]; // Which test runs to analyze
targetPromptId: string; // Which prompt needs improvement
analysisDepth?: 'shallow' | 'deep'; // How detailed (default: 'deep')
}gepa_get_pareto_frontier
Get the best prompt candidates that balance multiple goals.
{
minPerformance?: number; // Minimum quality threshold
limit?: number; // Max results to return (default: 10)
}gepa_select_optimal
Choose the best prompt for your specific use case.
{
taskContext?: string; // Describe your use case
performanceWeight?: number; // How much to prioritize accuracy (default: 0.7)
diversityWeight?: number; // How much to prioritize creativity (default: 0.3)
}gepa_record_trajectory
Log the results of prompt executions for analysis.
{
promptId: string; // Which prompt was used
taskId: string; // What task was performed
executionSteps: ExecutionStep[]; // What happened during execution
result: {
success: boolean; // Did it work?
score: number; // How well did it work?
};
}Backup & Recovery Tools
gepa_create_backup- Save current optimization stategepa_restore_backup- Restore from a previous backupgepa_list_backups- Show available backupsgepa_recovery_status- Check system healthgepa_integrity_check- Verify data integrity
📝 Basic Usage
Start Evolution: Use
gepa_start_evolutionwith your task descriptionRecord Results: Use
gepa_record_trajectoryto log how prompts performAnalyze Failures: Use
gepa_reflectto understand what went wrongGet Best Prompts: Use
gepa_select_optimalto find the best candidates
🔧 Environment Variables
# Optional performance tuning
GEPA_MAX_CONCURRENT_PROCESSES=3 # Parallel execution limit
GEPA_DEFAULT_POPULATION_SIZE=20 # Default prompt variants
GEPA_DEFAULT_GENERATIONS=10 # Default iterationsResources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.