User Prompt MCP server for AI agents

The MCP Server for Cursor provides an interactive interface that allows AI models to request additional input from users during generation without interrupting the process. It creates a seamless bridge between AI and users through a simple GUI dialog system compatible with both Linux and macOS.

Installation Requirements

Prerequisites

Before installing, ensure you have the necessary dependencies:

Linux: zenity must be installed
macOS: osascript (included by default)

Quick Installation

The simplest way to install the MCP server is using the automated installation script:

# 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

This script will:

Detect your operating system and architecture
Download the appropriate binary
Install it to a directory in your PATH
Make it executable

Installing from Source

If you prefer building from source (requires Go 1.18+):

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

Manual Binary Installation

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

Setting Up with Cursor

Configuring Cursor

Open Cursor and navigate to Settings
Find the MCP Servers section
Add a new server by editing the JSON configuration:

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

Save your changes and refresh Cursor

Adding Global Rules

Add the following to your global rules:

"Important - do not finish responding until explicitly told to do so, instead always use MCP input_user_prompt and wait for response in all cases, either you feel stuck, you have question or you finished work on a prompt - always communicate with the user using this MCP."

Configuration Options

Timeout Settings

By default, the server waits 20 minutes for user input before timing out. You can customize this:

Using command line flags:

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

Using environment variables:

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

Now when you use Cursor, the AI can request additional information from you during generation without interrupting its workflow.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "prompt" '{"command":"user-prompt-mcp"}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "prompt": {
            "command": "user-prompt-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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

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

3. Restart Claude Desktop for the changes to take effect