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. For the best results, add the following to your custom prompt: This will ensure Cline uses this MCP server to request user feedback before marking the task as completed. Hitting Save Configuration crea
Add this skill
npx mdskills install mrexodia/user-feedback-mcpWell-documented human-in-the-loop MCP server with clear setup instructions and practical workflow integration.
1# User Feedback MCP23Simple [MCP Server](https://modelcontextprotocol.io/introduction) to enable a human-in-the-loop workflow in tools like [Cline](https://cline.bot) and [Cursor](https://www.cursor.com). This is especially useful for developing desktop applications that require complex user interactions to test.4567## Prompt Engineering89For the best results, add the following to your custom prompt:1011> Before completing the task, use the user_feedback MCP tool to ask the user for feedback.1213This will ensure Cline uses this MCP server to request user feedback before marking the task as completed.1415## `.user-feedback.json`1617Hitting _Save Configuration_ creates a `.user-feedback.json` file in your project directory that looks like this:1819```json20{21 "command": "npm run dev",22 "execute_automatically": false23}24```2526This 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).2728## Installation (Cline)2930To install the MCP server in Cline, follow these steps (see screenshot):313233341. Install [uv](https://github.com/astral-sh/uv) globally:35 - Windows: `pip install uv`36 - Linux/Mac: `curl -LsSf https://astral.sh/uv/install.sh | sh`372. Clone this repository, for this example `C:\MCP\user-feedback-mcp`.383. Navigate to the Cline _MCP Servers_ configuration (see screenshot).394. Click on the _Installed_ tab.405. Click on _Configure MCP Servers_, which will open `cline_mcp_settings.json`.416. Add the `user-feedback-mcp` server:4243```json44{45 "mcpServers": {46 "github.com/mrexodia/user-feedback-mcp": {47 "command": "uv",48 "args": [49 "--directory",50 "c:\\MCP\\user-feedback-mcp",51 "run",52 "server.py"53 ],54 "timeout": 600,55 "autoApprove": [56 "user_feedback"57 ]58 }59 }60}6162```6364## Development6566```sh67uv run fastmcp dev server.py68```6970This will open a web interface at http://localhost:5173 and allow you to interact with the MCP tools for testing.7172## Available tools7374```75<use_mcp_tool>76<server_name>github.com/mrexodia/user-feedback-mcp</server_name>77<tool_name>user_feedback</tool_name>78<arguments>79{80 "project_directory": "C:/MCP/user-feedback-mcp",81 "summary": "I've implemented the changes you requested."82}83</arguments>84</use_mcp_tool>85```
Full transparency — inspect the skill content before installing.