Promptopia MCP server

Promptopia MCP is a comprehensive server that implements the Model Context Protocol (MCP) for managing AI prompt templates. It allows you to store, organize, and reuse prompts with variable substitution and supports sophisticated multi-message conversation structures, all while integrating seamlessly with MCP-compatible AI applications.

Key Features

• Centralized prompt management with filesystem persistence
• Multi-message conversation templates with role-based structures
• Intelligent variable substitution using {{variable}} syntax
• Native integration with MCP-compatible applications like Claude Desktop
• Support for both text and image content in templates

Installation Options

Using Smithery (Recommended)

Install Promptopia for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @lumile/promptopia-mcp --client claude

Using NPX

Add this configuration to your Claude Desktop config file:

{
  "mcpServers": {
    "promptopia-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "promptopia-mcp"
      ],
      "env": {
        "PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
      }
    }
  }
}

Replace <YOUR_PROMPTS_DIR> with the directory where you want to store your prompts.

Manual Installation

1. Clone the repository
2. Install dependencies:

npm install

3. Build the server:

npm run build

4. Add this configuration to your Claude Desktop config:

{
  "mcpServers": {
    "promptopia-mcp": {
      "command": "node",
      "args": [
        "/path/to/promptopia-mcp/build/index.js"
      ],
      "env": {
        "PROMPTS_DIR": "<YOUR_PROMPTS_DIR>"
      }
    }
  }
}

Using Promptopia MCP

Creating Prompts

With Promptopia MCP, you can create two types of prompts:

1. Single-content prompts - Simple text templates with variables
2. Multi-message prompts - Conversation templates with role-based structures

Variables are defined using double curly braces: {{variable_name}}. The server automatically detects these variables and allows you to substitute values when using the prompt.

Working with Variables

When using prompts through an MCP-compatible client, you'll be prompted to provide values for any variables detected in the template. These values will be substituted into the prompt before it's sent to the AI model.

Debugging

Since MCP servers communicate over stdio, debugging can be challenging. Use the MCP Inspector for better visibility:

npm run inspector

This will provide a URL to access debugging tools in your browser, making it easier to troubleshoot issues with your prompt templates or server configuration.

Advanced Usage

Managing Prompt Collections

All prompts are stored in the directory specified by the PROMPTS_DIR environment variable. This allows you to organize and back up your prompt templates as needed.

Multi-Message Conversation Templates

For more complex AI interactions, you can create multi-message templates that include both user and assistant messages. These templates can contain variables that span across multiple messages, creating reusable conversation patterns.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.