MCP.so
ログイン

Prompt Gen Mcp

@prompt-gen-mcp

Prompt Gen Mcp について

Transform simple questions into comprehensive, context-aware prompts

基本情報

カテゴリ

その他

トランスポート

stdio

公開者

prompt-gen-mcp

投稿者

Rishab Nandi

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "prompt-gen": {
      "command": "python",
      "args": [
        "/full/path/to/prompt-gen-mcp/src/prompt_gen_mcp/server.py"
      ],
      "env": {
        "GROQ_API_KEY": "gsk_your_groq_api_key_here",
        "TAVILY_API_KEY": "tvly_your_tavily_api_key_here",
        "PROMPTGEN_API_KEY": "pg_sk_your_promptgen_api_key_here"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Prompt Gen Mcp?

Prompt Gen Mcp is a local MCP server that transforms simple questions into comprehensive, context-aware prompts by combining advanced prompt engineering techniques from the PromptGen API with local code context. It is designed for developers using the Cursor IDE who want to create deeply structured prompts that leverage their actual codebase.

How to use Prompt Gen Mcp?

Install dependencies (pip install mcp sentence-transformers httpx groq), obtain API keys (PromptGen, GROQ, Tavily), configure Cursor’s MCP settings file with the server command and environment variables, then restart Cursor. Once running, press Cmd+Shift+P (Mac) or Ctrl+Shift+P (Windows/Linux) and invoke the MCP: enhance_prompt command with your question.

Key features of Prompt Gen Mcp

  • Local code context scanning (100% private, code never leaves your machine)
  • AI-powered selection of optimal prompt engineering techniques
  • Structured enhanced output with relevance scoring and code examples
  • Integration with Cursor IDE via true MCP architecture
  • Fallback support for offline operation

Use cases of Prompt Gen Mcp

  • Obtain structured optimization analysis with snippets from your own project
  • Receive comprehensive architecture comparisons grounded in your codebase
  • Get systematic debugging approaches that include relevant code context
  • Learn new concepts with examples drawn from your actual project files

FAQ from Prompt Gen Mcp

What dependencies does Prompt Gen Mcp require?

It requires Python packages: mcp, sentence-transformers, httpx, and groq. These are installed via pip in the server directory.

Which API keys are needed?

You need a PromptGen API key (starting with pg_sk_) from promptgenmcp-production.up.railway.app, a GROQ API key from console.groq.com, and a Tavily API key from tavily.com. All three are set as environment variables in the Cursor configuration.

How does Prompt Gen Mcp differ from basic prompting?

Compared to basic prompts, Prompt Gen Mcp offers full codebase context awareness, AI-powered technique selection, local privacy (code stays on your machine), structured output, code examples from your project, and relevance scoring for included context.

Where does my code go? Is privacy maintained?

All code scanning happens locally on your machine. Only the question text is sent to the PromptGen API to retrieve optimal techniques. Your code never leaves your environment.

What transport does Prompt Gen Mcp use?

It uses standard MCP stdio transport, with Cursor managing the server lifecycle automatically. No manual background service is needed.

コメント

「その他」の他のコンテンツ