Refines and structures prompts for large language models using the Anthropic API.
Refine Prompt is an intelligent prompt engineering tool that transforms ordinary prompts into powerful, structured instructions for any large language model (LLM). Using Claude's advanced capabilities, it enhances your prompts to produce exceptional results across all AI platforms.
🔑 Important: Your prompt must include the keyword "refine" to activate the enhancement process.
Example:
"refine, Create a function that calculates the factorial of a number"
npm install refine-prompt
You can install this MCP server directly through Smithery by visiting: Smithery - Refine Prompt
# Clone the repository
git clone https://github.com/felippefarias/refine-prompt.git
cd refine-prompt
# Install dependencies
npm install
Refine Prompt requires an Anthropic API key to access Claude's advanced capabilities:
export ANTHROPIC_API_KEY=your_anthropic_api_key
Without an API key, the tool will display an error message.
npm start
Or with MCP Inspector:
npx @modelcontextprotocol/inspector npm start
Transform your ideas into expertly crafted prompts. This powerful tool analyzes your input and generates a professionally engineered prompt that maximizes AI understanding and response quality.
Parameter | Description | Required |
---|---|---|
prompt | Your raw prompt that needs refinement (must include "refine" keyword) | ✅ |
language | For code-related prompts, specify the target programming language | ❌ |
{
"name": "rewrite_prompt",
"arguments": {
"prompt": "refine, Summarize the main points of the article titled \"The Future of AI\""
}
}
{
"name": "rewrite_prompt",
"arguments": {
"prompt": "refine, Create a function to convert temperature between Celsius and Fahrenheit",
"language": "typescript"
}
}
The server uses Claude 3 Sonnet by Anthropic to intelligently rewrite your prompts for better results. Every prompt must include the keyword "refine" to trigger the enhancement process.
It enhances your prompt by:
Feature | Description |
---|---|
🤖 AI-Powered Refinement | Leverages Claude 3.5 Sonnet's advanced capabilities to transform your prompts |
🔑 Activation with Keywords | Simply include "refine" in your prompt to trigger the enhancement |
🌐 Universal Compatibility | Optimizes prompts for any type of task or domain |
💻 Code-Specific Intelligence | Provides specialized enhancements for programming tasks when language is specified |
🔄 Seamless Integration | Works flawlessly with any LLM-powered application or workflow |
🎯 Precision-Focused | Uses 0.2 temperature setting to ensure reliable, consistent output quality |
📊 Structural Clarity | Adds logical organization, clear instructions, and proper formatting |
Add this to your claude_desktop_config.json
:
{
"mcpServers": {
"refine-prompt": {
"command": "npx",
"args": [
"-y",
"refine-prompt"
]
}
}
}
# Clone the repository
git clone https://github.com/felippefarias/refine-prompt.git
cd refine-prompt
# Install dependencies
npm install
# Run the server
node index.js
refine, Summarize the main points of the article titled "The Future of AI"
{
"prompt": "refine, Summarize the main points of the article titled \"The Future of AI\""
}
refine, Create a function that sorts an array of objects by a specific property
{
"prompt": "refine, Create a function that sorts an array of objects by a specific property",
"language": "typescript"
}
The tool will rewrite both prompts to be more structured and detailed for optimal results with any LLM.
Refine Prompt bridges the gap between human thinking and AI understanding. By transforming your natural language instructions into expertly engineered prompts, it helps you unlock the full potential of any language model. Whether you're a developer, content creator, researcher, or AI enthusiast, Refine Prompt gives you the power to communicate with AI more effectively.
Refine Prompt is licensed under the MIT License. You are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Single tool to control all 100+ API integrations, and UI components
A TypeScript library for integrating MCP with tools like LangChain and Zod, providing helpers for schema conversion and event streaming.
Boost security in your dev lifecycle via SAST, SCA, Secrets & IaC scanning with Cycode.
Access and control local iTerm2 terminal sessions.
Quickly retrieve SVGs using the Iconify API, with no external data files required.
Execute developer-defined bash scripts in a Dockerized environment for coding agents.
A collection of reference implementations for Model Context Protocol (MCP) servers in Typescript and Python, demonstrating MCP features and SDK usage.
Token-efficient access to OpenAPI/Swagger specs via MCP Resources
MCP server to provide Jira Tickets information to AI coding agents like Cursor.
An intelligent scientific reasoning framework that uses graph structures and Neo4j to perform advanced reasoning via the Model Context Protocol (MCP).