Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

user-feedback-mcp

MCP.Pizza Chef: mrexodia

User Feedback MCP is a lightweight MCP server designed to integrate human-in-the-loop feedback into applications like Cline and Cursor. It facilitates complex user interactions and feedback collection during task execution, making it ideal for desktop app development and testing. By prompting users for feedback before task completion, it enhances iterative development and quality assurance workflows.

Use This MCP server To

Integrate user feedback into AI task workflows Enable human-in-the-loop testing for desktop apps Collect real-time user input during task execution Improve task accuracy with user confirmation Facilitate iterative development with feedback loops Trigger feedback requests before task completion Customize feedback prompts in AI-driven tools Save user feedback configurations for projects

README

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.

Screenshot showing the feedback UI

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):

Screenshot showing installation steps

  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>

user-feedback-mcp FAQ

How do I integrate user-feedback-mcp into my project?
Install the server and configure your MCP client to call the user-feedback tool before task completion, as shown in the prompt engineering guide.
Can user-feedback-mcp be used with any MCP client?
It is designed to work seamlessly with tools like Cline and Cursor but can be adapted for other MCP clients supporting human-in-the-loop workflows.
How does user-feedback-mcp improve application testing?
By enabling real-time user feedback during task execution, it helps catch issues early and refine workflows interactively.
Is there a way to customize the feedback prompts?
Yes, you can modify the prompt engineering instructions to tailor the feedback requests to your specific application needs.
Does user-feedback-mcp support automated execution?
The configuration file allows toggling automatic execution, giving control over when feedback is requested.
What kind of feedback does the server collect?
It collects user responses related to task completion, confirmations, or any interactive input required by the workflow.
Can I save and reuse feedback configurations?
Yes, the server generates a .user-feedback.json file to save your feedback settings for consistent use across projects.
Is user-feedback-mcp compatible with multiple LLM providers?
While it focuses on human feedback, it integrates well with MCP clients that use OpenAI, Claude, Gemini, and other LLM providers.