User Feedback

Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor.

python

53

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mrexodia-user-feedback-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "c:\\MCP\\user-feedback-mcp",
        "run",
        "server.py"
      ]
    }
  }
}

You can run the User Feedback MCP to enable a human-in-the-loop workflow for testing and developing applications that require structured user feedback before task completion. It integrates with MCP-capable clients to prompt for feedback at the right moments, helping you iterate more effectively.

How to use

You connect to the MCP server from your MCP client (such as Cline or Cursor) and follow the on-screen prompts to request or gather user feedback. Use the server to trigger feedback prompts before completing tasks, ensuring that a human reviewer can approve or refine the result before moving forward.

How to install

Prerequisites: you need Python and a way to run utilities from the command line. You will install a helper tool called uv, clone the MCP server you are using, and configure your MCP client to load it.

# Install uv globally
# Windows
pip install uv

# Linux / macOS
curl -LsSf https://astral.sh/uv/install.sh | sh

# Clone the MCP server repository to a local path
# Example for Windows
# C:\MCP\user-feedback-mcp

# In Cline, open the MCP Servers configuration
# Go to the Installed tab, then Configure MCP Servers to edit cline_mcp_settings.json

# Add the user-feedback-mcp server (example snippet)
{
  "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 start for testing the MCP server
uv run fastmcp dev server.py

# When started, a web interface is available at http://localhost:5173 for testing MCP tools.

Additional configuration notes

Your configuration loads on startup. If you want the server to execute a command automatically, set execute_automatically in the .user-feedback.json file and provide the command to run. For multi-step tasks, use a Task-like structure to manage steps.

Available tools

user_feedback

Prompts users to provide feedback during task workflows to ensure tasks are reviewed before completion.