Prompt Ops MCP

A streamlined Model Context Protocol (MCP) server that optimizes prompts using meta-prompting techniques. This server can be easily integrated into Cursor and other MCP-compatible tools to enhance prompt quality and effectiveness.

Features

• Two-Turn Prompt Optimization: Transform basic prompts into sophisticated, structured requests using a simple two-turn approach

• Meta-Prompting Technique: Leverages the LLM's capabilities to apply optimization guidelines

• MCP Integration: Seamlessly integrates with Cursor and other MCP-compatible tools

• TypeScript: Built with TypeScript for type safety and better development experience

Installation

Via NPM (Recommended)

From Source

Usage

Integration with Cursor

Add the following to your Cursor MCP settings:

Direct Usage

How It Works: Two-Turn Optimization

The prompt optimizer uses a simple two-turn approach:

1. Turn 1: Provide your original prompt → Receive optimization guidelines

2. Turn 2: Provide the optimized prompt → Get it ready for use

Available Tool: promptenhancer

Parameters:

• originalPrompt: The prompt you want to optimize (for Turn 1)

• optimizedPrompt: The optimized prompt created by following the guidelines (for Turn 2)

Example Usage (Turn 1):

Example Usage (Turn 2):

Optimization Guidelines

The meta-prompting framework includes guidance for:

1. Clarifying Intent and Scope: Making implicit requirements explicit

2. Adding Structure and Organization: Breaking complex requests into clear sections

3. Enhancing with Reasoning Elements: Including step-by-step thinking instructions

4. Providing Context and Examples: Adding relevant background information

5. Setting Quality Standards: Defining success criteria and constraints

Example Transformation

See example-two-turn.md for a complete example of the two-turn optimization process.

Development

Setup

Development Scripts

Project Structure

Contributing

1. Fork the repository

2. Create a feature branch

3. Make your changes

4. Add tests for new functionality

5. Run npm run lint and npm run format

6. Submit a pull request

License

MIT License - see LICENSE file for details

Support

For issues and questions:

• GitHub Issues: Create an issue

• Discussions: Join the discussion

Changelog

v1.0.0

• Initial release with two-turn prompt optimization

• Full MCP integration support