User Feedback MCP Server

What does “User Feedback” MCP Server do?

The User Feedback MCP Server is a simple implementation of the Model Context Protocol (MCP) designed to enable a human-in-the-loop workflow within development tools like Cline and Cursor. Its main purpose is to facilitate direct user feedback during automated or AI-assisted development tasks. By integrating this server, workflows can prompt users for input, review, or approval at crucial steps, leveraging the strengths of both automation and human judgment. This is particularly useful for testing complex desktop applications or processes that require nuanced user evaluation before completion, ensuring quality and reducing errors by involving real users in the loop.

List of Prompts

• user_feedback prompt
  A recommended prompt pattern:

  Before completing the task, use the user_feedback MCP tool to ask the user for feedback.
  This prompt ensures that the LLM or workflow will invoke the user feedback tool to request explicit user approval or input prior to task completion.

List of Resources

• No explicit resources are mentioned in the repository documentation or code.

List of Tools

• user_feedback
  This tool allows the MCP server to request feedback from the user. It takes parameters such as project_directory (the path to the project) and a summary message (e.g., “I’ve implemented the changes you requested.”). This enables the workflow to halt and await human input before proceeding.

Use Cases of this MCP Server

• Human-in-the-loop task approval
  Automatically pause workflows to ask for user feedback or approval before proceeding, reducing errors and improving process quality.
• Desktop application testing
  Integrate with AI-assisted test automation to gather real user insights on UI changes or new features during the development process.
• Collaborative code review
  Prompt users for feedback on automated code changes, ensuring that modifications are aligned with human expectations.
• Workflow moderation in low-trust environments
  Require explicit user approval for sensitive or high-impact actions within automated pipelines.
• Iterative development feedback
  Continuously collect user impressions or suggestions during multi-step development tasks, aiding more responsive and adaptive workflows.

How to set it up

Windsurf

No setup instructions for Windsurf were found in the repository.

Claude

No setup instructions for Claude were found in the repository.

Cursor

No explicit step-by-step instructions for Cursor, but the server is designed to work with Cursor. Please refer to Cline setup as a reference.

Cline

1. Install prerequisites:
   • Install uv globally:
     • Windows: pip install uv
     • Linux/Mac: curl -LsSf https://astral.sh/uv/install.sh | sh
2. Clone the repository:
   • For example: C:\MCP\user-feedback-mcp
3. Navigate to MCP Servers configuration:
   • Open Cline and go to the MCP Servers config.
4. Configure the server:
   • Click Installed → Configure MCP Servers (opens cline_mcp_settings.json)
5. Add the server configuration:
   • Insert the following JSON:

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

Note about securing API keys:
There is no mention of API keys or secret management for this MCP server in the documentation or code.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "user-feedback-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “user-feedback-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

This MCP server is highly focused and easy to integrate for human-in-the-loop feedback, but lacks extensibility, resource exposure, and advanced features like API key management or sampling support. For developers needing only feedback gating, it’s excellent, but for broader MCP use it’s limited.

MCP Score

Rating: 6/10 – Very good for its narrow purpose, but lacking in broader MCP features and extensibility.