Prompt Ops MCP
Click on "Deploy 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 Ops MCP promptenhancer {"originalPrompt": "Write a Python function to calculate fibonacci numbers"}"
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 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
Related MCP server: PromptTuner MCP
Installation
Via NPM (Recommended)
npm install -g prompt-ops-mcpFrom Source
git clone <repository-url>
cd prompt-ops-mcp
npm install
npm run buildUsage
Integration with Cursor
Add the following to your Cursor MCP settings:
{
"mcpServers": {
"prompt-optimizer": {
"command": "npx",
"args": ["prompt-ops-mcp"]
}
}
}Direct Usage
# Run the server
npx prompt-ops-mcp
# Or if installed globally
prompt-ops-mcpHow It Works: Two-Turn Optimization
The prompt optimizer uses a simple two-turn approach:
Turn 1: Provide your original prompt → Receive optimization guidelines
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):
@prompt-ops promptenhancer {"originalPrompt": "Write a Python function to calculate fibonacci numbers"}Example Usage (Turn 2):
@prompt-ops promptenhancer {"optimizedPrompt": "Your optimized prompt here..."}Optimization Guidelines
The meta-prompting framework includes guidance for:
Clarifying Intent and Scope: Making implicit requirements explicit
Adding Structure and Organization: Breaking complex requests into clear sections
Enhancing with Reasoning Elements: Including step-by-step thinking instructions
Providing Context and Examples: Adding relevant background information
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
git clone <repository-url>
cd prompt-ops-mcp
npm installDevelopment Scripts
# Run in development mode
npm run dev
# Build the project
npm run build
# Run tests
npm run test
# Lint code
npm run lint
# Format code
npm run formatProject Structure
src/
├── index.ts # Main MCP server implementation
├── prompt-optimizer.ts # Core prompt optimization logic
└── types.ts # TypeScript type definitionsContributing
Fork the repository
Create a feature branch
Make your changes
Add tests for new functionality
Run
npm run lintandnpm run formatSubmit 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
Available Tools
1 toolpromptenhancerA
A prompt optimization tool that guides you through transforming basic prompts into comprehensive, well-structured prompts.
How it works:
First call: Provide an originalPrompt to receive optimization guidelines
The LLM follows the guidelines to create an optimized version
Second call: Provide the optimizedPrompt to get it ready for use
This tool uses a meta-prompting approach where the LLM does the actual optimization work.
Inputs: originalPrompt, optimizedPrompt.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'promptenhancer' has a clearly distinct and singular purpose: transforming basic prompts into optimized versions through a guided two-step process.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'promptenhancer' follows a clear and descriptive pattern, combining the target domain ('prompt') with the action ('enhancer'), and there are no other tools to cause inconsistency.
The server has only one tool, which feels thin for a server named 'Prompt Ops MCP' that might imply broader prompt operations. While the tool is well-described, a single tool limits the scope and could indicate incomplete coverage, as agents might expect more functionalities like prompt analysis, validation, or management.
The tool set is severely incomplete for the implied domain of prompt operations. It only offers enhancement via a specific meta-prompting approach, lacking other essential operations such as prompt validation, versioning, comparison, or basic CRUD management. This gap will likely cause agent failures when broader prompt-related tasks are needed.
Maintenance
Related MCP Connectors
A prompt engineer you talk to. It writes prompts, sharpens yours, and keeps them on your shelf.
Turn rough ideas into structured prompts for ChatGPT, Claude, Gemini, image and video AI.
The best prompt and the best model for the job, tested and improved by your coding agent.
Turns rough requests into sharp Role/Task/Context/Format prompts. Thai and English.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnhances and cleans raw prompts using AI to make them more clear, actionable, and effective. Provides quality assessment, suggestions, and supports both general and code-specific optimization modes.1MIT
- AlicenseBqualityDmaintenanceAnalyzes, refines, and optimizes prompts for AI assistants by fixing grammar, improving clarity, applying best practices like chain-of-thought and few-shot learning, and scoring prompt quality across multiple dimensions.337 npmMIT
- AlicenseNot gradedqualityBmaintenanceRefines and optimizes prompts for LLMs through adaptive questioning and intelligent clarification workflows. Supports multiple AI providers (Google, OpenAI, Anthropic, Groq, Qwen) with interactive prompt enhancement and targeted modifications.18 PyPI17MIT
- AlicenseBqualityDmaintenanceAutomatically analyzes and optimizes AI prompts by calculating clarity scores, detecting risks, asking clarifying questions, and adding domain-specific requirements to improve AI interaction quality.1MIT