User Feedback MCP

🚀 User Feedback MCP Server

A simple MCP Server that enables human-machine collaborative workflows in tools such as Cline and Cursor. This is particularly useful for desktop application development that requires complex user interaction testing.

🚀 Quick Start

✨ Features

This MCP server is designed to facilitate human-machine collaborative workflows in specific tools. It's especially beneficial for desktop application development where complex user interaction testing is needed.

💡 Prompt Engineering

For optimal results, add the following to your custom prompt:

Before completing the task, use the user feedback MCP tool to request feedback from the user.

This ensures that Cline uses this MCP server to request user feedback before marking a task as complete.

📄 .user-feedback.json

Clicking Save Configuration creates a .user-feedback.json file in the project directory, with content like this:

{
  "command": "npm run dev",
  "execute_automatically": false
}

This configuration is loaded at startup. If execute_automatically is enabled, the command will execute automatically (no need to manually click Run). For multi-step commands, it's recommended to use Task.

📦 Installation (Cline)

To install the MCP server in Cline, follow these steps (see screenshot):

1. Install uv globally:
   • Windows: pip install uv
   • Linux/Mac: curl -LsSf https://astral.sh/uv/install.sh | sh
2. Clone this repository, e.g., to C:\MCP\user-feedback-mcp.
3. Navigate to Cline's MCP Server configuration (see screenshot).
4. Click the Installed tab.
5. Click Configure MCP Server, which will open cline_mcp_settings.json.
6. Add the following to mcpServers:

{
  "mcpServers": {
    "github.com/mrexodia/user-feedback-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "c:\\MCP\\user-feedback-mcp",
        "run",
        "server.py"
      ],
      "timeout": 600,
      "autoApprove": [
        "user_feedback"
      ]
    }
  }
}

💻 Usage Examples

Basic Usage

uv run fastmcp dev server.py

This will open a web interface at http://localhost:5173 and allow you to interact with the MCP tool for testing.

Advanced Usage

<use_mcp_tool>
<server_name>github.com/mrexodia/user-feedback-mcp</server_name>
<tool_name>user_feedback</tool_name>
<arguments>
{
  "project_directory": "C:/MCP/user-feedback-mcp",
  "summary": "I have implemented the changes you requested."
}
</arguments>
</use_mcp_tool>