What is Prompts Mcp Server

The prompts-mcp-server is a Model Context Protocol (MCP) server designed for managing and providing prompts. It enables users and large language models (LLMs) to easily add, retrieve, and manage prompt templates stored as markdown files with YAML frontmatter support.

Use cases

Use cases include managing prompt templates for chatbots, automating content generation, and providing structured prompts for AI models in research and development.

How to use

To use prompts-mcp-server, clone the repository from GitHub, install the dependencies, build the TypeScript code, and run tests to ensure it works. Then, configure your MCP client to connect to the server and restart the client to start using the prompts.

Key features

Key features include the ability to add, retrieve, list, and delete prompts, file-based storage in markdown format, real-time caching, support for structured metadata via YAML frontmatter, full TypeScript implementation, modular architecture, and comprehensive testing with high code coverage.

Where to use

prompts-mcp-server can be used in various fields such as software development, natural language processing, and any application that requires prompt management for LLMs.

Prompts MCP Server

A Model Context Protocol (MCP) server for managing and providing prompts. This server allows users and LLMs to easily add, retrieve, and manage prompt templates stored as markdown files with YAML frontmatter support.

Quick Start

# 1. Install from NPM
npm install -g prompts-mcp-server

# 2. Add to your MCP client config (e.g., Claude Desktop)
# Add this to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
  "mcpServers": {
    "prompts-mcp-server": {
      "command": "prompts-mcp-server"
    }
  }
}

# 3. Restart your MCP client and start using the tools!

Features

• Add Prompts: Store new prompts as markdown files with YAML frontmatter
• Retrieve Prompts: Get specific prompts by name
• List Prompts: View all available prompts with metadata preview
• Delete Prompts: Remove prompts from the collection
• File-based Storage: Prompts are stored as markdown files in the prompts/ directory
• Real-time Caching: In-memory cache with automatic file change monitoring
• YAML Frontmatter: Support for structured metadata (title, description, tags, etc.)
• TypeScript: Full TypeScript implementation with comprehensive type definitions
• Modular Architecture: Clean separation of concerns with dependency injection
• Comprehensive Testing: 95 tests with 84.53% code coverage

Installation

Option 1: From NPM (Recommended)

Install the package globally from NPM:

npm install -g prompts-mcp-server

This will make the prompts-mcp-server command available in your system.

After installation, you need to configure your MCP client to use it. See MCP Client Configuration.

Option 2: From GitHub (for development)

# Clone the repository
git clone https://github.com/tanker327/prompts-mcp-server.git
cd prompts-mcp-server

# Install dependencies
npm install

# Build the TypeScript code
npm run build

# Test the installation
npm test

Option 3: Direct Download

1. Download the latest release from GitHub
2. Extract to your desired location
3. Run installation steps from Option 2.

Verification

After installation, verify the server works:

# Start the server (should show no errors)
npm start

# Or test with MCP Inspector
npx @modelcontextprotocol/inspector prompts-mcp-server

Testing

Run the comprehensive test suite:

npm test

Run tests with coverage:

npm run test:coverage

Watch mode for development:

npm run test:watch

MCP Tools

The server provides the following tools:

add_prompt

Add a new prompt to the collection. If no YAML frontmatter is provided, default metadata will be automatically added.

• name (string): Name of the prompt
• content (string): Content of the prompt in markdown format with optional YAML frontmatter

create_structured_prompt

Create a new prompt with guided metadata structure and validation.

• name (string): Name of the prompt
• title (string): Human-readable title for the prompt
• description (string): Brief description of what the prompt does
• category (string, optional): Category (defaults to “general”)
• tags (array, optional): Array of tags for categorization (defaults to [“general”])
• difficulty (string, optional): “beginner”, “intermediate”, or “advanced” (defaults to “beginner”)
• author (string, optional): Author of the prompt (defaults to “User”)
• content (string): The actual prompt content (markdown)

get_prompt

Retrieve a prompt by name.

• name (string): Name of the prompt to retrieve

list_prompts

List all available prompts with metadata preview. No parameters required.

delete_prompt

Delete a prompt by name.

• name (string): Name of the prompt to delete

Usage Examples

Once connected to an MCP client, you can use the tools like this:

Method 1: Quick prompt creation with automatic metadata

// Add a prompt without frontmatter - metadata will be added automatically
add_prompt({
  name: "debug_helper",
  content: `# Debug Helper

Help me debug this issue by:
1. Analyzing the error message
2. Suggesting potential causes
3. Recommending debugging steps`
})
// This automatically adds default frontmatter with title "Debug Helper", category "general", etc.

Method 2: Structured prompt creation with full metadata control

// Create a prompt with explicit metadata using the structured tool
create_structured_prompt({
  name: "code_review",
  title: "Code Review Assistant",
  description: "Helps review code for best practices and potential issues",
  category: "development",
  tags: ["code", "review", "quality"],
  difficulty: "intermediate",
  author: "Development Team",
  content: `# Code Review Prompt

Please review the following code for:
- Code quality and best practices
- Potential bugs or issues
- Performance considerations
- Security vulnerabilities

## Code to Review
[Insert code here]`
})

Method 3: Manual frontmatter (preserves existing metadata)

// Add a prompt with existing frontmatter - no changes made
add_prompt({
  name: "custom_prompt",
  content: `---
title: "Custom Assistant"
category: "specialized"
tags: ["custom", "specific"]
difficulty: "advanced"
---

# Custom Prompt Content
Your specific prompt here...`
})

Other operations

// Get a prompt
get_prompt({ name: "code_review" })

// List all prompts (shows metadata preview)
list_prompts({})

// Delete a prompt
delete_prompt({ name: "old_prompt" })

File Structure

prompts-mcp-server/
├── src/
│   ├── index.ts          # Main server orchestration
│   ├── types.ts          # TypeScript type definitions
│   ├── cache.ts          # Caching system with file watching
│   ├── fileOperations.ts # File I/O operations
│   └── tools.ts          # MCP tool definitions and handlers
├── tests/
│   ├── helpers/
│   │   ├── testUtils.ts  # Test utilities
│   │   └── mocks.ts      # Mock implementations
│   ├── cache.test.ts     # Cache module tests
│   ├── fileOperations.test.ts # File operations tests
│   ├── tools.test.ts     # Tools module tests
│   └── index.test.ts     # Integration tests
├── prompts/              # Directory for storing prompt markdown files
│   ├── code_review.md
│   ├── debugging_assistant.md
│   └── api_design.md
├── dist/                 # Compiled JavaScript output
├── CLAUDE.md            # Development documentation
├── package.json
├── tsconfig.json
└── README.md

Architecture

The server uses a modular architecture with the following components:

• PromptCache: In-memory caching with real-time file change monitoring via chokidar
• PromptFileOperations: File I/O operations with cache integration
• PromptTools: MCP tool definitions and request handlers
• Type System: Comprehensive TypeScript types for all data structures

YAML Frontmatter Support

Prompts can include structured metadata using YAML frontmatter:

---
title: "Prompt Title"
description: "Brief description of the prompt"
category: "development"
tags: ["tag1", "tag2", "tag3"]
difficulty: "beginner" | "intermediate" | "advanced"
author: "Author Name"
version: "1.0"
---

# Prompt Content

Your prompt content goes here...

MCP Client Configuration

This server can be configured with various MCP-compatible applications. Here are setup instructions for popular clients:

Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "prompts-mcp-server": {
      "command": "prompts-mcp-server",
      "env": {
        "PROMPTS_FOLDER_PATH": "/path/to/your/prompts/directory"
      }
    }
  }
}

Cline (VS Code Extension)

Add to your Cline MCP settings in VS Code:

{
  "cline.mcp.servers": {
    "prompts-mcp-server": {
      "command": "prompts-mcp-server",
      "env": {
        "PROMPTS_FOLDER_PATH": "/path/to/your/prompts/directory"
      }
    }
  }
}

Continue.dev

In your ~/.continue/config.json:

{
  "mcpServers": [
    {
      "name": "prompts-mcp-server",
      "command": "prompts-mcp-server",
      "env": {
        "PROMPTS_FOLDER_PATH": "/path/to/your/prompts/directory"
      }
    }
  ]
}

Zed Editor

In your Zed settings (~/.config/zed/settings.json):

{
  "assistant": {
    "mcp_servers": {
      "prompts-mcp-server": {
        "command": "prompts-mcp-server",
        "env": {
          "PROMPTS_DIR": "/path/to/your/prompts/directory"
        }
      }
    }
  }
}

Custom MCP Client

For any MCP-compatible application, use these connection details:

• Protocol: Model Context Protocol (MCP)
• Transport: stdio
• Command: prompts-mcp-server
• Environment Variables:
  • PROMPTS_FOLDER_PATH: Custom directory for storing prompts (optional, defaults to ./prompts)

Development/Testing Setup

For development or testing with the MCP Inspector:

# Install MCP Inspector
npm install -g @modelcontextprotocol/inspector

# Run the server with inspector
npx @modelcontextprotocol/inspector prompts-mcp-server

Docker Configuration

Create a docker-compose.yml for containerized deployment:

version: '3.8'
services:
  prompts-mcp-server:
    build: .
    environment:
      - PROMPTS_FOLDER_PATH=/app/prompts
    volumes:
      - ./prompts:/app/prompts
    stdin_open: true
    tty: true

Server Configuration

• The server automatically creates the prompts/ directory if it doesn’t exist
• Prompt files are automatically sanitized to use safe filenames (alphanumeric characters, hyphens, and underscores only)
• File changes are monitored in real-time and cache is updated automatically
• Prompts directory can be customized via the PROMPTS_FOLDER_PATH environment variable

Environment Variables

Variable	Description	Default
PROMPTS_FOLDER_PATH	Custom directory to store prompt files (overrides default)	(not set)
NODE_ENV	Environment mode	production

Note: If PROMPTS_FOLDER_PATH is set, it will be used as the prompts directory. If not set, the server defaults to ./prompts relative to the server location.

Requirements

• Node.js 18.0.0 or higher
• TypeScript 5.0.0 or higher
• Dependencies:
  • @modelcontextprotocol/sdk ^1.0.0
  • gray-matter ^4.0.3 (YAML frontmatter parsing)
  • chokidar ^3.5.3 (file watching)

Development

The project includes comprehensive tooling for development:

• TypeScript: Strict type checking and modern ES modules
• Vitest: Fast testing framework with 95 tests and 84.53% coverage
• ESLint: Code linting (if configured)
• File Watching: Real-time cache updates during development

Troubleshooting

Common Issues

“Module not found” errors

# Ensure TypeScript is built
npm run build

# Check that dist/ directory exists and contains .js files
ls dist/

MCP client can’t connect

1. Verify the server starts without errors: npm start
2. Check the correct path is used in client configuration
3. Ensure Node.js 18+ is installed: node --version
4. Test with MCP Inspector: npx @modelcontextprotocol/inspector prompts-mcp-server

Permission errors with prompts directory

# Ensure the prompts directory is writable
mkdir -p ./prompts
chmod 755 ./prompts

File watching not working

• On Linux: Install inotify-tools
• On macOS: No additional setup needed
• On Windows: Ensure Windows Subsystem for Linux (WSL) or native Node.js

Debug Mode

Enable debug logging by setting environment variables:

# Enable debug mode
DEBUG=* node dist/index.js

# Or with specific debug namespace
DEBUG=prompts-mcp:* node dist/index.js

Getting Help

1. Check the GitHub Issues
2. Review the test files for usage examples
3. Use MCP Inspector for debugging client connections
4. Check your MCP client’s documentation for configuration details

Performance Tips

• The server uses in-memory caching for fast prompt retrieval
• File watching automatically updates the cache when files change
• Large prompt collections (1000+ files) work efficiently due to caching
• Consider using SSD storage for better file I/O performance

Community Variants & Extensions

Project	Maintainer	Extra Features
smart-prompts-mcp	@jezweb	GitHub-hosted prompt libraries, advanced search & composition, richer TypeScript types, etc.

👉 Have you built something cool on top of prompts-mcp-server?
Open an issue or PR to add it here so others can discover your variant!

License

MIT