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., "@Refine Prompt refine, write a Python script to automate weekly email reports"
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.
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"
Related MCP server: prompte-mcp
npm install refine-promptYou 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 installRefine Prompt requires an Anthropic API key to access Claude's advanced capabilities:
export ANTHROPIC_API_KEY=your_anthropic_api_keyWithout an API key, the tool will display an error message.
npm startOr with MCP Inspector:
npx @modelcontextprotocol/inspector npm startTransform 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 |
| Your raw prompt that needs refinement (must include "refine" keyword) | ✅ |
| 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:
📐 Adding clear structure and context
📝 Specifying requirements and expectations
🔍 Including domain-specific considerations
🌐 Optimizing for any LLM understanding
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.jsrefine, 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.
This tool MUST be used whenever a user asks to refine, rewrite, improve, enhance, or optimize a prompt. It transforms raw prompts into more effective versions that are clearer, more detailed, and better structured to improve results from Large Language Models (LLMs). When users mention 'refine prompt' or similar phrases, use this tool.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The raw user prompt that needs rewriting. | |
| language | No | Optional: The primary programming language if the prompt is code-related (e.g., typescript, python). Helps tailor coding prompts. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes the tool's function and transformation process but lacks details on behavioral traits such as rate limits, error handling, or output format. The description doesn't contradict annotations (none exist), but it provides only basic operational context without deeper behavioral insights.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with the core purpose stated in the first sentence. Each sentence adds value: the first defines the tool's function, the second explains the transformation, and the third provides usage triggers. There's minimal redundancy, though it could be slightly more concise by combining some phrases without losing clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (2 parameters, no output schema, no annotations), the description covers purpose and usage well but lacks details on behavioral aspects and output. It doesn't explain what the refined prompt looks like or any constraints, which would be helpful since no output schema exists. This makes it adequate but with gaps in completeness for an agent's full understanding.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the input schema already documents both parameters thoroughly. The description doesn't add any additional meaning or context beyond what the schema provides (e.g., no examples, edge cases, or usage tips for parameters). This meets the baseline score of 3, as the schema handles parameter documentation adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('refine, rewrite, improve, enhance, or optimize a prompt') and identifies the resource ('prompt'). It explicitly distinguishes what the tool does ('transforms raw prompts into more effective versions') and how it achieves this ('clearer, more detailed, and better structured to improve results from LLMs'). No siblings exist, but the description is comprehensive and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidelines with clear triggers ('whenever a user asks to refine, rewrite, improve, enhance, or optimize a prompt') and specific phrases to watch for ('refine prompt' or similar phrases). It directly states 'MUST be used' for these cases, offering definitive when-to-use instructions. Since no sibling tools exist, no alternative guidance is needed, making this complete for the context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.2.0refine_promptWith only one tool, there is no possibility of ambiguity or overlap with other tools. The tool's purpose is clearly defined and distinct by default.
The single tool name 'refine_prompt' follows a consistent verb_noun pattern, and there are no other tools to create inconsistency.
A single tool feels thin for a server named 'Refine Prompt', as it suggests a narrow scope with no additional functionality like versioning, history, or batch processing. This is borderline too few for a dedicated server.
The tool covers the core action of refining prompts, but there are notable gaps such as no ability to list, retrieve, or manage previous refinements, which limits workflow completeness for a prompt refinement domain.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
MCP server for generating rough-draft project plans from natural-language prompts.
Hosted MCP server connecting claude.ai, ChatGPT and other AI apps to your own computer
Cloudflare Workers MCP server: ai-prompt-optimizer
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/FelippeFarias/refine-prompt'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
