User Feedback MCP: Effortless Collaboration & Smarter AI Integration

User Feedback MCP streamlines human-in-the-loop workflows for Cline, Cursor, and more—effortless collaboration meets smarter AI.

Visit Repository

✨ Developer Tools

4.1(104 reviews)

156 saves

72 comments

This tool saved users approximately 8822 hours last month!

About User Feedback MCP

What is User Feedback MCP: Effortless Collaboration & Smarter AI Integration?

User Feedback MCP is the Swiss Army knife of collaborative development, enabling seamless human-in-the-loop workflows in tools like Cline and Cursor. Think of it as your project’s digital middleman—politely interrupting AI-driven tasks to ask users, “Hey, does this align with your vision?” before finalizing work. Perfect for teams building complex apps where user input is as vital as caffeine.

How to Use User Feedback MCP: Effortless Collaboration & Smarter AI Integration?

Firstly, install the uv runtime (we won’t judge if you mutter obscenities during setup). Clone this repo, configure Cline’s MCP settings like a sysadmin configuring their first firewall, and voilà—you’ve got a feedback loop that’s smoother than a well-rehearsed stand-up routine. The magic happens via that .user-feedback.json file, which acts as your automation on/off switch.

User Feedback MCP Features

Key Features of User Feedback MCP: Effortless Collaboration & Smarter AI Integration?

Autopilot Mode: Let the execute_automatically flag do the heavy lifting—no more manual button mashing.
AI Whisperer: Integrates with tools to pause workflows and fetch user feedback via MCP’s elegant UI (no clunky pop-ups).
Task Tamer: Handles multi-step commands gracefully when paired with Taskfiles—because who likes juggling 17 terminal tabs?

Use Cases of User Feedback MCP: Effortless Collaboration & Smarter AI Integration?

User Feedback MCP FAQ

FAQ from User Feedback MCP: Effortless Collaboration & Smarter AI Integration?

Why not just use Slack for feedback? You could, but then we’d miss the joy of programmatic precision. MCP ensures feedback is contextually tied to exact tasks, not lost in a sea of channel noise.

Does it work on Mars? We’ve tested lunar deployment—Mars is pending Elon’s next rocket. For Earth-based setups, works with standard gravity levels.

My cat walked on the keyboard during setup… Reinstall uv and blame quantum physics. Seriously, though, check the MCP docs for troubleshooting.

Content

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

Install uv globally:
* Windows: pip install uv
* Linux/Mac: curl -LsSf https://astral.sh/uv/install.sh | sh
Clone this repository, for this example C:\MCP\user-feedback-mcp.
Navigate to the Cline MCP Servers configuration (see screenshot).
Click on the Installed tab.
Click on Configure MCP Servers , which will open cline_mcp_settings.json.
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>