Skip to main content
Glama
sayll

dev-prompt-mcp

by sayll
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

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

Related MCP server: MCP-YNU FastMCP Server

📦 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

在 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

Available Tools

2 tools
get_prompt_names获取 Prompt 列表B

获取所有可用的prompt名称

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden but only states the action. It does not disclose behavioral traits such as read-only nature, side effects, or any prerequisites. The description adds no value beyond the tool's name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that efficiently conveys the tool's purpose with no superfluous words. It earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (0 parameters, no output schema), the description is minimally adequate. However, it does not mention the format of the returned names or any ordering, leaving room for interpretation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (0 parameters), so the description does not need to add parameter details. Baseline of 3 applies as the description provides no additional semantic context beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb '获取' (get) and resource 'prompt名称' (prompt names), making the purpose specific. However, it does not differentiate from the sibling tool 'reload_prompts', which could cause ambiguity for the AI agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the sibling tool 'reload_prompts'. The description lacks any context about appropriate usage scenarios or conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

reload_prompts重新加载 PromptsA

重新加载所有预设的prompts

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, and the description only states 'reload all preset prompts', lacking details on side effects, persistence, or whether it disrupts existing operations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with no redundancy, front-loading the verb and object effectively.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple parameterless tool, the description covers the basic action. However, it could mention that prompts are reloaded from storage, but overall it is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema coverage is 100%. The description adds no additional meaning but is sufficient given the absence of parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The tool description clearly states the action 'reload' and the resource 'prompts', distinguishing it from the sibling tool 'get_prompt_names' which likely lists prompts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not indicate scenarios where reloading is needed or mention any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 2 tool updatesv1.0.0
    • First observedget_prompt_names
    • First observedreload_prompts
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

The two tools, get_prompt_names and reload_prompts, have clearly distinct purposes: one retrieves names, the other reloads prompts. There is no overlap or ambiguity.

Naming Consistency5/5

Both tool names follow a consistent verb_noun pattern in snake_case, making them predictable and easy to understand.

Tool Count3/5

With only 2 tools, the set is on the lower end of appropriate. It feels thin for a prompt management server, which typically would have more operations, but it could be a minimal interface for simple listing and reloading.

Completeness2/5

The tool surface lacks essential operations for prompt management, such as retrieving prompt content, creating, updating, or deleting prompts. Agents cannot perform basic CRUD tasks, leading to significant gaps.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • Lodestar MCP Server

    kanlanc
    F
    license
    C
    quality
    D
    maintenance
    This is an MCP server that facilitates building tools for interacting with various APIs and workflows, supporting Python-based development with potential for customizable prompts and user configurations.
    1
    -
  • MCP-YNU FastMCP Server by ynu

    MCP-YNU FastMCP Serverofficial

    ynu
    A
    license
    Not graded
    quality
    D
    maintenance
    A dynamic MCP server implementation that automatically loads tools, resources, and prompts from their respective directories, allowing for easy extension and configuration.
    MIT

  • MCP Inspector Server

    acnlabs
    F
    license
    Not graded
    quality
    D
    maintenance
    A basic MCP server template that provides a foundation for building custom tools, resources, and prompts. Serves as a starting point for developers to create their own MCP server functionality.
    -

  • Prompt Registry MCP

    stevengonsalvez
    A
    license
    Not graded
    quality
    C
    maintenance
    A lightweight, file-based server for managing and serving personal prompt templates with variable substitution support via the Model Context Protocol. It allows users to store, update, and organize prompts in a local directory through integrated MCP tools and CLI assistants.
    20
    7
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sayll/dev-prompt-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server