M

MCP实时开发提示

@yuyao1999/rt-prompt-mcp
0 Stars 42 次浏览 yuyao1999 更新于 2026-08-23

一种模型上下文协议服务器,为后端开发、前端开发和通用任务提供专业的提示建议,帮助大型语言模型生成更好的内容。

MCP 服务配置

复制以下 JSON 到 OPClaw 或其他 MCP 客户端的配置文件中即可使用

{
  "mcpServers": {
    "rt-prompt-mcp": {
      "args": [],
      "command": "rt-prompt-mcp"
    }
  }
}

可用工具 (4 个)

该服务在 MCP 协议中暴露的工具,AI 可按需调用

get_backend_suggestions 3 个参数

该工具无需必填参数,直接调用即可

get_frontend_suggestions 3 个参数

该工具无需必填参数,直接调用即可

get_general_suggestions 2 个参数

该工具无需必填参数,直接调用即可

get_ui_design_suggestions 3 个参数

该工具无需必填参数,直接调用即可

服务介绍

RT-Prompt-MCP

RT-Prompt-MCP is a server based on the Model Context Protocol (MCP) that focuses on providing development and design-related prompt suggestions.

Features

  • Provides domain-specific prompt suggestions to help LLMs generate more relevant content
  • Supports prompts for backend development, frontend development, and general scenarios
  • Easy integration with MCP protocol-compliant clients
  • Developed using TypeScript, ensuring type safety

Installation

Global installation:

bash
npm install -g rt-prompt-mcp

Usage

Running as a Command Line Tool

After installation, simply run:

bash
rt-prompt-mcp

Integrating as an MCP Server with MCP Clients

Configure in MCP protocol-supported applications (e.g., Claude Desktop):

json
{
"mcpServers": {
"rt-prompt-mcp": {
"command": "rt-prompt-mcp",
"args": []
}
}
}

Tool Description

This MCP Server provides three main tools:

  1. get-backend-suggestions: Get backend development-related prompt suggestions

    • context: The current context or task description
    • databaseType: Type of database (e.g., MySQL, PostgreSQL, etc.)
    • language: Programming language (e.g., Java, Python, etc.)
  2. get-frontend-suggestions: Get frontend development-related prompt suggestions

    • context: The current context or task description
    • framework: Frontend framework (e.g., React, Vue, etc.)
    • deviceType: Device type (e.g., mobile, desktop, etc.)
  3. get-general-suggestions: Get general scenario-related prompt suggestions

    • context: The current context or task description
    • taskType: Type of task (e.g., code generation, document generation, etc.)

Examples

For example, to get suggestions for MySQL database design:

Use the get-backend-suggestions tool and provide the following parameters:

  • context: "Creating database table structures for users and orders"
  • databaseType: "MySQL"
  • language: "SQL"

Development

Prerequisites

  • Node.js 16+
  • npm or yarn

Local Development

  1. Clone the repository:

    bash
    git clone https://github.com/yourusername/rt-prompt-mcp.git
    cd rt-prompt-mcp

  2. Install dependencies:

    bash
    npm install

  3. Build the project:

    bash
    npm run build

  4. Test locally:
    bash
    npm start

License

MIT

相关 MCP 服务