Skip to main content
Glama
Pretty Prompt MCP Server

Pretty Prompt MCP Server

by charliemday

Pretty Prompt MCP 服务器

MCP 服务器,将您的 Pretty Prompt 库和提示词改进器暴露给 Cursor、Claude Desktop 及其他 MCP 客户端。

工具

工具

描述

list_library_prompts

列出库中已保存的提示词

save_to_library

将提示词保存到库中

list_library_folders

列出库中的文件夹

create_library_folder

创建一个文件夹(可选择嵌套在父文件夹下)

rename_library_folder

重命名现有文件夹

move_prompt_to_folder

将提示词移动到文件夹中(或移至根目录)

improve_prompt

改进/优化提示词(消耗您的 Pretty Prompt 额度)

Related MCP server: MCP Prompt Manager

设置

1. 生成 API 密钥

前往 pretty-prompt.com/settings/mcp 创建一个 API 密钥。

2. 构建

npm install
npm run build

3. 配置 Cursor

添加到您的 Cursor MCP 配置(~/.cursor/mcp.json 或项目中的 .cursor/mcp.json):

{
  "mcpServers": {
    "pretty-prompt": {
      "command": "npx",
      "args": ["-y", "@pretty-prompt/mcp@latest"],
      "env": {
        "PRETTY_PROMPT_API_KEY": "pp_mcp_..."
      }
    }
  }
}

对于本地开发,覆盖生产默认值:

"env": {
  "PRETTY_PROMPT_API_KEY": "pp_mcp_...",
  "PRETTY_PROMPT_BACKEND_URL": "http://0.0.0.0:8000",
  "PRETTY_PROMPT_SUPABASE_URL": "http://127.0.0.1:54321",
  "PRETTY_PROMPT_SUPABASE_ANON_KEY": "your-local-anon-key"
}

环境变量

变量

必需

默认值

描述

PRETTY_PROMPT_API_KEY

是

—

来自设置的 API 密钥(pp_mcp_...)

PRETTY_PROMPT_BACKEND_URL

否

https://production.pretty-prompt.com

FastAPI 后端 URL

PRETTY_PROMPT_SUPABASE_URL

否

https://api.pretty-prompt.com

Supabase 项目 URL

PRETTY_PROMPT_SUPABASE_ANON_KEY

否

生产环境匿名密钥

Supabase 匿名密钥

PRETTY_PROMPT_ANALYTICS

否

已启用

设置为 false 以禁用 PostHog 分析

PRETTY_PROMPT_POSTHOG_KEY

否

生产环境 PostHog 密钥

覆盖 PostHog 项目密钥

分析

MCP 服务器会发送 PostHog 事件(即发即忘),包括:

事件

触发时机

mcp_server_started

每次服务器进程启动并完成身份验证时

mcp_first_connected

该机器上某个 API 密钥首次成功连接时

mcp_tool_called

每次工具调用时(名称、成功与否、耗时、经过处理的参数)

事件会关联到 MCP 访问令牌对应的用户邮箱。提示词文本永远不会被发送——仅发送长度和标志位。

通过 PRETTY_PROMPT_ANALYTICS=false 在本地禁用。

覆盖环境变量以指向本地服务:

PRETTY_PROMPT_BACKEND_URL=http://0.0.0.0:8000
PRETTY_PROMPT_SUPABASE_URL=http://127.0.0.1:54321

确保后端已设置 SUPABASE_JWT_SECRET 并应用了 mcp_api_keys 迁移。

Available Tools

5 tools
improve_promptA

Improve and refine a prompt using Pretty Prompt. Returns a polished prompt (flattened text plus structured sections), an explanation, and optional follow-up questions. Uses the user's prompt credits. To refine further, call again with question_answers from the follow_up_questions.

Inputs: prompt (required), category, provider, save_to_library, +3 more.

list_library_foldersA

List folders in the user's Pretty Prompt library. Use this before move_prompt_to_folder to get folder UUIDs. Folders are a flat list; parent_id indicates nesting (null = root).

Inputs: no named parameters.

list_library_promptsB

List saved prompts from the user's Pretty Prompt library.

Inputs: limit, offset, search, favorites_only.

move_prompt_to_folderA

Move a library prompt into a folder, or to the library root. Call list_library_folders first to resolve folder UUIDs. Pass folder_id=null to remove the prompt from its folder.

Inputs: prompt_id (required), folder_id.

save_to_libraryA

Save a prompt to the user's Pretty Prompt library.

Inputs: prompt (required), title.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: listing prompts, saving prompts, listing folders, moving prompts, and improving prompts. There is no overlap or ambiguity between them.

    Naming Consistency4/5

    Most tools follow a clear verb_noun or verb_preposition_noun pattern (list_library_prompts, save_to_library, move_prompt_to_folder), but the mix of styles (list_*, save_to_*, move_*_to_*, improve_*) is slightly inconsistent. Still, names are readable and predictable.

    Tool Count5/5

    With 5 tools, the server is well-scoped for a library management and prompt improvement service. Each tool has a clear purpose and none are redundant.

    Completeness4/5

    The set covers listing, saving, organizing, and improving prompts. Missing delete/update operations for prompts or folders are minor gaps that agents can work around, but the core workflow is complete.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Allows users to save, organize, and manage AI prompts, folders, and tags directly within MCP-compatible tools like Claude and Cursor. It supports version history tracking, prompt searching, and the ability to save public templates to a personal collection.
      20
      17 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables reading, searching, installing, and managing ParetoStudio prompts, agents, and skills from Claude Code, Cursor, or any MCP client, and can install agents/skills as files into Claude Code or Codex projects.
      MIT