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., "@Coding Prompt Engineer MCP Server rewrite 'add user authentication' for Python with best practices"
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.
This Model Context Protocol (MCP) server provides a tool to rewrite coding prompts for optimal results with Cursor AI and other AI IDEs, using Claude by Anthropic.
npm installYou can install this MCP server directly through Smithery by visiting: https://smithery.ai/server/@hireshBrem/prompt-engineer-mcp-server
Related MCP server: Session Buddy
The server requires an Anthropic API key to use Claude for formatting. Set it as an environment variable:
export ANTHROPIC_API_KEY=your_anthropic_api_keyIf no API key is provided, the server will throw an error indicating the missing API key.
npm startOr with MCP Inspector:
npx @modelcontextprotocol/inspector npm startThis tool takes a raw prompt and rewrites it for optimal results with Cursor AI and other AI IDEs.
prompt (required): The raw user's prompt that needs rewriting
language (required): The programming language of the code
{
"name": "rewrite_coding_prompt",
"arguments": {
"prompt": "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. It enhances your prompt by:
Adding clear structure and context
Specifying requirements and expectations
Including language-specific considerations
Optimizing for AI IDE understanding
Intelligent Prompt Engineering: Uses Claude 3 Sonnet to rewrite prompts for optimal results
Language-Aware: Customizes prompts based on target programming language
Easy Integration: Works seamlessly with Cursor and other AI IDEs
Low Temperature Setting: Uses 0.2 temperature for consistent, structured output
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"cursor-prompt-engineer": {
"command": "npx",
"args": [
"-y",
"cursor-prompt-engineer"
]
}
}
}# Clone the repository
git clone https://github.com/yourusername/cursor-prompt-engineer.git
cd cursor-prompt-engineer
# Install dependencies
npm install
# Run the server
node index.jsInput:
Create a function that sorts an array of objects by a specific propertyWith arguments:
{
"prompt": "Create a function that sorts an array of objects by a specific property",
"language": "typescript"
}The tool will rewrite the prompt to be more structured and detailed for optimal results with your AI IDE.
This MCP server is licensed under the MIT License. This means 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.
Rewrites user's coding prompts before passing to AI IDE (e.g. Cursor AI) to get the best results from AI IDE.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The raw user's prompt that needs rewriting | |
| language | Yes | The programming language of the code |
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 mentions the tool 'rewrites' prompts but doesn't explain how the rewriting works (e.g., formatting changes, clarity improvements, or specific optimizations), what the output looks like, or any constraints like rate limits or error conditions. This leaves significant gaps in understanding the tool's behavior.
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 a single, efficient sentence that directly states the tool's purpose and goal. It's front-loaded with the main action and avoids unnecessary details. However, it could be slightly more structured by explicitly mentioning the parameters or output, but overall, it's concise and to the point.
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 complexity (rewriting prompts for AI IDEs), the description is insufficient. With no annotations and no output schema, it fails to explain key aspects like the rewriting process, output format, or any behavioral traits. The description alone doesn't provide enough context for an AI agent to understand how to effectively use or interpret results from this tool.
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?
The input schema has 100% description coverage, with clear documentation for both parameters ('prompt' and 'language'). The description doesn't add any additional meaning or context beyond what the schema provides, such as examples or formatting tips. With high schema coverage, the baseline score of 3 is appropriate, as the schema handles the 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: 'Rewrites user's coding prompts before passing to AI IDE (e.g. Cursor AI) to get the best results from AI IDE.' It specifies the verb ('rewrites'), resource ('user's coding prompts'), and goal ('to get the best results from AI IDE'). However, without sibling tools, it cannot demonstrate differentiation from alternatives, so it doesn't reach the highest score.
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 no guidance on when to use this tool versus other methods or tools. It states the tool's function but offers no context about prerequisites, alternatives, or specific scenarios where it's most effective. This lack of usage instructions limits its practical utility for an AI agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently has perfect naming consistency, as there are no other tools to compare it against. The naming follows a clear verb_noun pattern.
A single tool is too few for a server with a broad purpose like 'Coding Prompt Engineer,' which suggests potential for multiple operations such as analyzing, optimizing, or testing prompts. This minimal set feels incomplete and under-scoped.
The server's domain implies handling coding prompts, but the single rewrite tool leaves significant gaps. Missing operations might include validating prompts, generating examples, or providing feedback, making the surface severely incomplete for the stated purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Persistent memory for Claude Code and Cursor. Stop re-explaining your project every session.
Shared memory for AI coding agents. Save once, reuse from Cursor, Claude Code, Codex.
AI code review for GitHub PRs with an MCP autofix loop for Claude Code and Cursor
Persistent context for Claude. Your AI always knows your projects and next actions across sessions.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/hireshBrem/prompt-engineer-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
