User Prompt MCP

🚀 User Prompt MCP Server

This is a Model Context Protocol (MCP) server implemented for Cursor, allowing requests for user input during the generation process without terminating it. It serves as a bridge between the AI model and the user, offering a more interactive experience.

🚀 Quick Start

The project implements an MCP server, enabling Cursor (or other compatible clients) to request more input from the user during the generation process. It integrates via stdio and supports multiple platforms (tested on Linux and macOS).

✨ Features

• User Input Prompt: Allows the AI to request more information during the generation process.
• Simple GUI: Displays prompt information in a dialog box, supporting text line breaks.
• Cross - platform: Works on Linux and macOS.
• Stdio Transmission: Integrates with Cursor.

📦 Installation

Prerequisites

• For GUI functionality:
  • Linux: zenity
  • macOS: osascript (built - in)

Quick Installation (Recommended)

Use our installation script to automatically download the pre - compiled binary for your system:

# Install the latest version
curl -sSL https://raw.githubusercontent.com/nazar256/user-prompt-mcp/main/install.sh | bash

# Or install a specific version
curl -sSL https://raw.githubusercontent.com/nazar256/user-prompt-mcp/main/install.sh | bash -s -- -v v1.0.0

The installation script will:

• Detect your operating system and architecture (Linux or macOS, amd64 or arm64).
• Download the appropriate pre - compiled binary.
• Install it in the appropriate directory and add it to the PATH environment variable.
• Set it as an executable file.

Installation from Source

If you want to build from source (requires Go 1.18+):

go install github.com/nazar256/user-prompt-mcp/cmd/user-prompt-mcp@latest

Manual Installation

You can also directly download the pre - compiled binary from the Releases page.

💻 Usage Examples

Using with Cursor

1. Open Cursor and go to the settings.
2. Navigate to the MCP server section and add a new server configuration (edit JSON):

{
  "mcpServers": {
    "prompt": {
      "command": "user-prompt-mcp"
    }
  }
}

3. Save and refresh.
4. Add to the global rules, for example: "Important - Do not end the response until explicitly instructed. Always use MCP input_user_prompt to wait for the user's reply in all cases. Always communicate via this MCP whenever you are confused, have questions, or finish the prompt task."

Configuration

The server can be configured via command - line flags or environment variables:

Timeout Settings

By default, the server will time out after waiting for 20 minutes. You can customize the timeout as follows:

• Command - line flag: --timeout <seconds>

user-prompt-mcp --timeout 600  # Set the timeout to 10 minutes

• Environment variable: USER_PROMPT_TIMEOUT=<seconds>

export USER_PROMPT_TIMEOUT=1800  # Set the timeout to 30 minutes
user-prompt-mcp

Now, Cursor's AI can request additional user input during the generation process without terminating it.

📄 License

MIT

Acknowledgments

• Model Context Protocol
• mark3labs/mcp-go