JamesANZ/system-prompts-mcp-server

> **Access system prompts from AI tools in your workflow.** Browse and fetch prompts from Devin, Cursor, Claude, GPT, and more. Model-aware suggestions help you find the perfect prompt for your LLM.
An MCP (Model Context Protocol) server that exposes a collection of system prompts, summaries, and tool definitions from popular AI tools as MCP tools for AI coding environments like Cursor and Claude Desktop.
Why Use System Prompts MCP?
- 🔍 **Automatic Discovery** – Every prompt in prompts/ is automatically exposed as an MCP tool
- 🎯 **Model-Aware Suggestions** – Get prompt recommendations based on your LLM (Claude, GPT, Gemini, etc.)
- 📚 **Comprehensive Collection** – Access prompts from Devin, Cursor, Claude, GPT, and more
- 🚀 **Easy Setup** – One-click install in Cursor or simple manual setup
- 🔧 **Extensible** – Add your own prompts and they're automatically available
Quick Start
Ready to explore system prompts? Install in seconds:
**Install in Cursor (Recommended):**
🔗 Install in Cursor
**Or install manually:**
Features
Core Tools
- **list_prompts** – Browse available prompts with filters (service, flavor, provider)
- **get_prompt_suggestion** – Get ranked prompt suggestions for your LLM and keywords
- ** - - ** – Direct access to any prompt (e.g., cursor-agent-system, devin-summary)
Automatic Discovery
- Scans prompts/ directory for .txt, .md, .yaml, .yml, .json files
- Each file becomes a dedicated MCP tool
- Infers metadata (service, variant, LLM family, persona hints)
Persona Activation
- Each tool call includes a reminder for the model to embody the loaded prompt
- Helps models behave like the original service (Devin, Cursor, etc.)
Installation
Cursor (One-Click)
Click the install link above or use:
Manual Installation
**Requirements:** Node.js 18+ and npm
Claude Desktop
Add to claude_desktop_config.json:
**macOS**: ~/Library/Application Support/Claude/claude_desktop_config.json
**Windows**: %APPDATA%\Claude\claude_desktop_config.json
Restart Claude Desktop after configuration.
Usage Examples
List Available Prompts
Browse prompts with optional filters:
Get Prompt Suggestions
Find the best prompt for your LLM and use case:
Access a Specific Prompt
Call a prompt directly by its tool name:
Get structured metadata only:
Adding Your Own Prompts
Add prompts by placing files in the prompts/ directory:
**Supported formats:** .txt, .md, .yaml, .yml, .json
**Directory structure:**
- Directory names become the service name
- File names create tool variants
- Files are automatically classified as system prompts, tools, or summaries
After adding prompts, restart the MCP server. Use list_prompts to find your custom prompts.
**Custom directory:** Set PROMPT_LIBRARY_ROOT environment variable to use a different location.
Use Cases
- **AI Tool Developers** – Reference and adapt prompts from successful AI tools
- **Researchers** – Study how different tools structure their system prompts