dev-prompt-mcp

dev-prompt-mcp

An MCP server that registers customizable prompt templates as tools for natural language interaction. It supports hot-reloading and easy extension via YAML or JSON files to automate tasks like code review, refactoring, and content summarization.

Category
Visit Server

README

dev-prompt-mcp

一个基于 MCP (Model Context Protocol) 的 Prompt 管理服务器,将常用的 Prompt 模板注册为 MCP 工具,通过自然语言对话即可调用。

npm version License: MIT

✨ 特性

  • 🚀 TypeScript 开发 - 完整的类型支持,代码更健壮
  • 📦 Prompt 即工具 - 所有 Prompt 自动注册为 MCP 工具,支持参数化调用
  • 🔄 热加载 - 支持命令式动态加载 Prompt,无需重启服务
  • 🧩 易于扩展 - 添加 YAML/JSON 文件即可扩展新 Prompt
  • 🛠️ 开发友好 - 支持开发模式、Inspector 调试

📦 安装

方式 1:NPM 全局安装

npm install -g dev-prompt-mcp

方式 2:NPX 直接运行(推荐)

无需安装,直接在 MCP 配置中使用 npx

方式 3:从源码安装

git clone https://github.com/sayll/dev-prompt-mcp.git
cd dev-prompt-mcp
pnpm install
pnpm run build

🔧 MCP 配置

方式 1:使用 npx(推荐)

适用于 Cursor / Windsurf / Augment / Trae 等,编辑对应的 mcp_config.json

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

方式 2:全局安装后使用

{
  "mcpServers": {
    "dev-prompt": {
      "command": "dev-prompt-mcp"
    }
  }
}

方式 3:从源码运行

{
  "mcpServers": {
    "dev-prompt": {
      "command": "node",
      "args": ["/your/path/to/dev-prompt-mcp/dist/index.js"]
    }
  }
}

Raycast

  1. 搜索 install server (MCP)
  2. Name: dev-prompt
  3. Command: npx
  4. Arguments: dev-prompt-mcp

📁 项目结构

dev-prompt-mcp/
├── src/
│   ├── index.ts              # 服务器入口
│   ├── PromptManager.ts      # Prompt 管理器(加载、注册、监听)
│   ├── types.ts              # TypeScript 类型定义
│   └── prompts/              # Prompt 模板目录
│       ├── gen_summarize.yaml
│       ├── gen_apifox_api_service.yaml
│       ├── i18n_chinese_transform.yaml
│       ├── code_review.yaml
│       └── code_refactoring.yaml
├── dist/                     # 编译输出目录
├── package.json
├── tsconfig.json
└── README.md

🛠️ 开发

安装依赖

pnpm install

可用脚本

命令 说明
pnpm run dev 开发模式(tsx watch,自动重启)
pnpm run dev:inspector 使用 MCP Inspector 调试
pnpm run build 编译 TypeScript
pnpm run build:watch 监听模式编译
pnpm run start 运行编译后的代码

📝 内置 Prompt

Prompt 说明
gen_summarize 生成内容摘要
gen_apifox_api_service 通过 Apifox MCP 获取接口并生成 API 服务代码
i18n_chinese_transform 将页面中文通过 i18n 转义,管理多语言文件
code_review 代码审查
code_refactoring 代码重构

🛠️ 管理工具

工具 说明
reload_prompts 重新加载所有 Prompt(支持热更新)
get_prompt_names 获取当前所有可用 Prompt 名称

📄 扩展 Prompt

src/prompts/ 目录下创建 YAML 或 JSON 文件:

name: my_custom_prompt
description: 这个 Prompt 的用途说明
arguments:
  - name: input
    description: 输入参数说明
    required: false
messages:
  - role: user
    content:
      type: text
      text: |
        你的 Prompt 内容
        支持参数占位符:{{input}}

🏗️ 技术栈

  • Runtime: Node.js (ESM)
  • Language: TypeScript
  • MCP SDK: @modelcontextprotocol/sdk
  • 配置解析: yaml, zod
  • 文件操作: fs-extra

📦 依赖

生产依赖:

  • @modelcontextprotocol/sdk - MCP 服务器核心 SDK
  • fs-extra - 增强的文件操作
  • yaml - YAML 解析
  • zod - Schema 验证

开发依赖:

  • typescript - TypeScript 编译器
  • tsx - 开发模式运行 TS
  • @types/node, @types/fs-extra - 类型定义

📄 License

MIT

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured