User Feedback MCP

What is User Feedback MCP about?

User Feedback MCP provides a lightweight MCP server that tools like Cline and Cursor can call to solicit real‑time user feedback. It stores configuration in a .user-feedback.json file and can automatically run commands based on that configuration, making it ideal for testing desktop applications that require complex user interactions.

How to use User Feedback MCP?

1. Install the required runtime (uv) globally.
2. Clone the repository to a local path (e.g., C:\MCP\user-feedback-mcp).
3. Configure Cline’s MCP servers by adding an entry for github.com/mrexodia/user-feedback-mcp with the appropriate uv command and arguments.
4. Run the server (uv run fastmcp dev server.py). The web UI will be available at http://localhost:5173.
5. Within your custom prompt, include the instruction to call the user_feedback MCP tool before completing a task.
6. Use the generated .user-feedback.json to define a command that should be executed automatically or manually after receiving feedback.

Key Features

• Simple MCP server exposing a user_feedback tool.
• Automatic or manual command execution via .user-feedback.json configuration.
• Web UI for testing and interacting with MCP tools.
• Ready‑made Cline installation steps with screenshots.
• Supports multi‑step commands through external task runners (e.g., Task).

Use Cases

• Desktop application testing: Pause a workflow, ask the user for clarification, and resume based on their input.
• Iterative UI design: Gather real‑time feedback on UI changes before committing code.
• Complex command automation: Execute long‑running build or deployment commands only after user confirmation.
• Prototyping AI‑assisted tools: Integrate human feedback loops into AI‑driven code generation pipelines.

FAQ

• Do I need to use uv? Yes, the server is built with Python and uv is the recommended package manager for quick installation.
• Can I run the server with Node.js/npm? No, the project is Python‑based; use uv as described.
• What does execute_automatically do? When set to true, the command specified in .user-feedback.json runs immediately after feedback is received, without manual interaction.
• How do I integrate with Cline? Add the provided JSON snippet to cline_mcp_settings.json under mcpServers and ensure the path points to your cloned repository.
• Can I customize the feedback UI? The UI is served from the built‑in web interface; you can modify the front‑end code in the repository if needed.

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>