Pretty Prompt MCP Server
Pretty Prompt MCP Server
MCP-Server, der Ihre Pretty Prompt-Bibliothek und den Prompt-Verbesserer für Cursor, Claude Desktop und andere MCP-Clients bereitstellt.
Werkzeuge
Werkzeug | Beschreibung |
| Listet gespeicherte Prompts aus Ihrer Bibliothek auf |
| Speichert einen Prompt in Ihrer Bibliothek |
| Listet Ordner in Ihrer Bibliothek auf |
| Erstellt einen Ordner (optional unter einem übergeordneten Ordner) |
| Benennt einen vorhandenen Ordner um |
| Verschiebt einen Prompt in einen Ordner (oder ins Stammverzeichnis) |
| Verbessert/verfeinert einen Prompt (verwendet Ihre Pretty Prompt-Guthaben) |
Related MCP server: MCP Prompt Manager
Einrichtung
1. API-Schlüssel generieren
Gehen Sie zu pretty-prompt.com/settings/mcp und erstellen Sie einen API-Schlüssel.
2. Erstellen
npm install
npm run build3. Cursor konfigurieren
Fügen Sie zu Ihrer Cursor-MCP-Konfiguration hinzu (~/.cursor/mcp.json oder Projekt-.cursor/mcp.json):
{
"mcpServers": {
"pretty-prompt": {
"command": "npx",
"args": ["-y", "@pretty-prompt/mcp@latest"],
"env": {
"PRETTY_PROMPT_API_KEY": "pp_mcp_..."
}
}
}
}Für die lokale Entwicklung überschreiben Sie die Produktionsstandards:
"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"
}Umgebungsvariablen
Variable | Erforderlich | Standard | Beschreibung |
| Ja | — | API-Schlüssel aus den Einstellungen ( |
| Nein |
| FastAPI-Backend-URL |
| Nein |
| Supabase-Projekt-URL |
| Nein | Produktions-Anon-Key | Supabase-Anon-Key |
| Nein | aktiviert | Auf |
| Nein | Produktions-PostHog-Schlüssel | PostHog-Projektschlüssel überschreiben |
Analysen
Der MCP-Server sendet PostHog-Ereignisse (Fire-and-Forget) für:
Ereignis | Wann |
| Jedes Mal, wenn der Serverprozess startet und sich authentifiziert |
| Erste erfolgreiche Verbindung für einen API-Schlüssel auf diesem Rechner |
| Jeder Tool-Aufruf (Name, Erfolg, Dauer, bereinigte Parameter) |
Ereignisse werden der E-Mail des Benutzers aus dem MCP-Zugriffstoken zugeordnet. Prompt-Text wird nie gesendet – nur Längen und Flags.
Lokal deaktivieren mit PRETTY_PROMPT_ANALYTICS=false.
Umgebungsvariablen überschreiben, um auf lokale Dienste zu verweisen:
PRETTY_PROMPT_BACKEND_URL=http://0.0.0.0:8000
PRETTY_PROMPT_SUPABASE_URL=http://127.0.0.1:54321Stellen Sie sicher, dass das Backend SUPABASE_JWT_SECRET gesetzt hat und die Migration mcp_api_keys angewendet wurde.
Available Tools
5 toolsimprove_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.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | The prompt text to improve | |
| category | No | Optional category (General, Image, Video, Vibe Coding, Research, Agent, System Prompt) | |
| provider | No | Optional target provider (e.g. openai, perplexity, lovable) | |
| save_to_library | No | If true, also save the improved prompt to the library | |
| question_answers | No | Map of follow-up question → selected answers for a refine pass | |
| context_snippet_ids | No | Specific context snippet IDs to include | |
| include_context_snippets | No | Include the user's saved context snippets |
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).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
list_library_promptsB
List saved prompts from the user's Pretty Prompt library.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Page size (default: all) | |
| offset | No | Pagination offset | |
| search | No | Search in title, prompt text, or origin | |
| favorites_only | No | Return only favourite prompts |
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.
| Name | Required | Description | Default |
|---|---|---|---|
| folder_id | No | Destination folder UUID, or null for root | |
| prompt_id | Yes | Library prompt ID (from list_library_prompts) |
save_to_libraryA
Save a prompt to the user's Pretty Prompt library.
| Name | Required | Description | Default |
|---|---|---|---|
| title | No | Optional display title | |
| prompt | Yes | The prompt text to save |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
5 tool updates
v0.3.0- First observed
improve_prompt - First observed
list_library_folders - First observed
list_library_prompts - First observed
move_prompt_to_folder - First observed
save_to_library
TDQS
Scored across 5 tools
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.
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.
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.
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.
Maintenance
Related MCP Connectors
Your prompt library in any MCP client: list, fetch, save and version prompt templates.
Your versioned prompt library: search, read, save and version prompts from Claude Code.
Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.
Your prompt library inside your AI: 1,000+ pro templates, frameworks, vocab & pipelines.
Related MCP Servers
- AlicenseAqualityDmaintenanceAllows 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.2027 npmMIT
- AlicenseBqualityDmaintenanceEnables AI models like Claude to manage local prompt files with CRUD operations, fuzzy search, categorization, templates, version control, and favorites.325MIT
- AlicenseNot gradedqualityDmaintenanceEnables searching, retrieving, and managing prompts for Claude Code through natural language, with tools for adding, updating, and deleting prompts.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables 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.39 npmMIT