User Feedback

What is User Feedback MCP?

User Feedback MCP is a Model Context Protocol (MCP) server designed to integrate human feedback into AI-powered development workflows. It facilitates a "human-in-the-loop" approach, allowing developers to solicit and incorporate user feedback directly within tools like Cline and Cursor, particularly for testing desktop applications with intricate user interactions.

How to use User Feedback MCP?

To use User Feedback MCP, you need to install it within your Cline environment. This involves:

1. Installing uv globally: Use pip install uv for Windows or curl -LsSf https://astral.sh/uv/install.sh | sh for Linux/Mac.
2. Cloning the repository: Clone the user-feedback-mcp repository to your local machine.
3. Configuring Cline: Navigate to Cline's MCP Servers configuration, open cline_mcp_settings.json, and add the user-feedback-mcp server configuration, specifying the command to run the server (e.g., uv --directory c:\MCP\user-feedback-mcp run server.py).

For optimal results, you can add a prompt engineering snippet to your custom prompt: Before completing the task, use the user_feedback MCP tool to ask the user for feedback. This ensures Cline prompts for user feedback before marking a task as complete.

Key Features of User Feedback MCP

• Human-in-the-loop workflow: Seamlessly integrates human feedback into AI development processes.
• Compatibility: Designed to work with tools like Cline and Cursor.
• Configuration file generation: Automatically creates a .user-feedback.json file in your project directory upon saving the configuration, allowing for command execution and automation.
• Automated execution: The execute_automatically flag in the .user-feedback.json file enables instant execution of specified commands on startup.
• Developer-friendly: Provides a development mode with a web interface for testing MCP tools.

Use Cases of User Feedback MCP

• Developing desktop applications: Particularly useful for testing applications that require complex user interactions.
• Iterative development: Enables continuous feedback loops for refining AI models and applications.
• Quality assurance: Incorporates human review to improve the quality and accuracy of AI-generated content or actions.
• Prompt engineering: Guides AI tools to solicit user feedback at specific points in a task workflow.

FAQ about User Feedback MCP

Q: What is the purpose of the .user-feedback.json file? A: This file is created when you save the configuration and allows you to define a command to be executed. If execute_automatically is set to true, the command will run automatically on startup.

Q: How can I test the User Feedback MCP during development? A: You can run uv run fastmcp dev server.py to open a web interface at http://localhost:5173, allowing you to interact with and test the MCP tools.

User Feedback MCP

Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test.

Prompt Engineering

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

Before completing the task, use the user_feedback MCP tool to ask the user for feedback.

This will ensure Cline uses this MCP server to request user feedback before marking the task as completed.

.user-feedback.json

Hitting Save Configuration creates a .user-feedback.json file in your project directory that looks like this:

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

This configuration will be loaded on startup and if execute_automatically is enabled your command will be instantly executed (you will not have to click Run manually). For multi-step commands you should use something like 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, for this example C:\MCP\user-feedback-mcp.
3. Navigate to the Cline MCP Servers configuration (see screenshot).
4. Click on the Installed tab.
5. Click on Configure MCP Servers, which will open cline_mcp_settings.json.
6. Add the user-feedback-mcp server:

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

Development

uv run fastmcp dev server.py

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

Available tools

<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've implemented the changes you requested."
}
</arguments>
</use_mcp_tool>