PromptForge is an intelligent prompt optimization middleware that enhances user prompts before they reach AI models. It analyzes prompt intent and applies domain-specific optimization patterns to improve clarity, context, and response quality. Key features of PromptForge: - **Smart Pattern Matching**: Automatically detects prompt intent and applies relevant enhancements like role additions, context injection, and structural improvements - **Domain-Specific Tuning**: Pre-configured optimization patterns for marketing copy, data analysis, tax/accounting, and code generation - **Analytics & Performance Tracking**: Monitors optimization metrics and prompt performance over time using Supabase - **Custom Pattern Management**: Create, update, and manage custom optimization patterns stored via JSONBin.io - **Before/After Testing**: Compare original and optimized prompts to evaluate improvement PromptForge integrates with external services for pattern storage and analytics, requiring zero configuration to start while remaining fully customizable for advanced use cases.

PromptForge MCP Server

Intelligent prompt optimization middleware that enhances user prompts before execution.

Features

Setup

1. Install Dependencies

npm install

2. Configure External Services

#### JSONBin.io (Pattern Storage) 1. Create account at https://jsonbin.io 2. Create a new bin with initial patterns 3. Copy your bin ID and API key

#### Supabase (Analytics) 1. Create account at https://supabase.com 2. Create a new project 3. Create a table called prompt_analytics with this schema: - id (uuid, primary key) - original_prompt (text) - optimized_prompt (text) - domain (text) - confidence (float) - modifications (json) - user_feedback (json, nullable) - performance_metrics (json, nullable) - created_at (timestamp with timezone)

3. Environment Variables

Copy .env.example to .env and fill in your API credentials:

cp .env.example .env

4. Test Your Setup

npm test

Available Tools

optimize_prompt

{
  "tool": "optimize_prompt",
  "arguments": {
    "prompt": "Write an email about our services",
    "domain": "marketing_copy",
    "context": {
      "company": "Your Company",
      "audience": "B2B customers"
    }
  }
}

get_patterns

{
  "tool": "get_patterns",
  "arguments": {
    "domain": "marketing_copy"
  }
}

update_pattern

{
  "tool": "update_pattern",
  "arguments": {
    "domain": "custom_domain",
    "pattern": {
      "triggerKeywords": ["keyword1", "keyword2"],
      "enhancements": [
        {
          "type": "role_addition",
          "value": "You are an expert..."
        }
      ]
    }
  }
}

get_analytics_summary

{
  "tool": "get_analytics_summary",
  "arguments": {
    "timeRange": "week",
    "domain": "marketing_copy"
  }
}

test_optimization

{
  "tool": "test_optimization",
  "arguments": {
    "prompt": "analyze our sales data",
    "showDiff": true
  }
}

Deployment to mcpify.ai

1. Create New MCP Server on mcpify.ai - Name: promptforge - Description: "Intelligent prompt optimization for consistent AI outputs"

2. Upload Files - Copy the contents of server.js to mcpify.ai - Add environment variables from your .env file

3. Configure Tools - The server automatically exposes all tools defined in getTools()

Default Patterns

The server includes pre-configured patterns for:

For Schapira CPA Integration

This server is optimized for use with Schapira CPA's services:

{
  "context": {
    "company": "Schapira CPA",
    "industry": "Tax and Accounting Services",
    "audience": "Mid-market owner-operated businesses",
    "tone": "professional"
  }
}

License

MIT - Feel free to customize for your needs!