user feedback mcp

Local 2025-08-31 23:49:32 0
Developer Tools @mrexodia/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.

x000D 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.x000D x000D Screenshot showing the feedback UIx000D x000D

Prompt Engineering_x000D_

x000D For the best results, add the following to your custom prompt:x000D x000D

Before completing the task, use the user_feedback MCP tool to ask the user for feedback.x000D x000D This will ensure Cline uses this MCP server to request user feedback before marking the task as completed.x000D x000D

.user-feedback.jsonx000D

x000D Hitting Save Configuration creates a .user-feedback.json file in your project directory that looks like this:x000D x000D 

{_x000D_
  "command": "npm run dev",_x000D_
  "execute_automatically": false_x000D_
}_x000D_
```_x000D_
_x000D_
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](https://taskfile.dev)._x000D_
_x000D_
## Installation (Cline)_x000D_
_x000D_
To install the MCP server in Cline, follow these steps (see screenshot):_x000D_
_x000D_
![Screenshot showing installation steps](https://github.com/mrexodia/user-feedback-mcp/blob/main/.github/cline-installation.png?raw=true)_x000D_
_x000D_
1. Install [uv](https://github.com/astral-sh/uv) globally:_x000D_
   - Windows: `pip install uv`_x000D_
   - Linux/Mac: `curl -LsSf https://astral.sh/uv/install.sh | sh`_x000D_
2. Clone this repository, for this example `C:MCPuser-feedback-mcp`._x000D_
3. Navigate to the Cline _MCP Servers_ configuration (see screenshot)._x000D_
4. Click on the _Installed_ tab._x000D_
5. Click on _Configure MCP Servers_, which will open `cline_mcp_settings.json`._x000D_
6. Add the `user-feedback-mcp` server:_x000D_
_x000D_
```json_x000D_
{_x000D_
  "mcpServers": {_x000D_
    "github.com/mrexodia/user-feedback-mcp": {_x000D_
      "command": "uv",_x000D_
      "args": [_x000D_
        "--directory",_x000D_
        "c:MCPuser-feedback-mcp",_x000D_
        "run",_x000D_
        "server.py"_x000D_
      ],_x000D_
      "timeout": 600,_x000D_
      "autoApprove": [_x000D_
        "user_feedback"_x000D_
      ]_x000D_
    }_x000D_
  }_x000D_
}_x000D_
_x000D_
```_x000D_
_x000D_
## Development_x000D_
_x000D_
```sh_x000D_
uv run fastmcp dev server.py_x000D_
```_x000D_
_x000D_
This will open a web interface at http://localhost:5173 and allow you to interact with the MCP tools for testing._x000D_
_x000D_
## Available tools_x000D_
_x000D_
```_x000D_
<use_mcp_tool>_x000D_
<server_name>github.com/mrexodia/user-feedback-mcp</server_name>_x000D_
<tool_name>user_feedback</tool_name>_x000D_
<arguments>_x000D_
{_x000D_
  "project_directory": "C:/MCP/user-feedback-mcp",_x000D_
  "summary": "I've implemented the changes you requested."_x000D_
}_x000D_
</arguments>_x000D_
</use_mcp_tool>_x000D_

[
  {
    "description": "Request user feedback for a given project directory and summary",
    "inputSchema": {
      "properties": {
        "project_directory": {
          "description": "Full path to the project directory",
          "title": "Project Directory",
          "type": "string"
        },
        "summary": {
          "description": "Short, one-line summary of the changes",
          "title": "Summary",
          "type": "string"
        }
      },
      "required": [
        "project_directory",
        "summary"
      ],
      "title": "user_feedbackArguments",
      "type": "object"
    },
    "name": "user_feedback"
  }
]