interactive_feedbackLABSCO SUMMARY
The clarification happens inside one request, not a new one.
Because the question travels as a tool call, several rounds of back-and-forth fit inside a single request — the author's argument for why asking beats guessing wrong and being asked to try again. It needs a desktop session: this is a Qt window on your machine, so it will not work on a headless host.
What it is
A desktop feedback window driven by one tool. When the assistant hits an ambiguity it calls interactive_feedback, a three-pane window opens on your machine, and your answer returns inside the same request.
What you get
interactive_feedback— the assistant pauses mid-task and puts the question to you- Predefined options you can choose with
Ctrl+1-5, so a decision costs one keystroke - A three-column window: message content, suggested options, and project information with Git status
- A configuration file at
~/.interactive_feedback_mcp/config.jsonfor theme, language, font, window size and pane ratios - Separate log files for the main log, errors, performance and project context, with a
manage_logs.pyscript to view, search, analyse and export them
Requirements
Python 3.10+ with PySide6 and FastMCP, launched through uv: uv --directory <YOUR_PATH_TO_INTERACTIVE_FEEDBACK_MCP> run server.py. Give the entry a generous timeout — the sample config uses 600 — and add interactive_feedback to autoApprove. Windows 10+, macOS 12+ or Ubuntu 20.04+.
Setup effort
Build from source — git clone https://github.com/zengxiaolou/interactive-feedback-mcp.git
USE CASES
01
Stopping an agent before it builds the wrong thing
When the requirement is ambiguous, the assistant asks and waits rather than picking an interpretation.
02
Choosing between implementations quickly
The assistant offers the options as a list; you pick one with a keystroke instead of typing an explanation.
03
Confirming before something destructive runs
Put a confirmation step in front of the operation, with the project and Git status visible in the same window.
04
Working out why the window failed to appear
Read the error and performance logs, or search across all of them for the message you saw.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. interactive_feedback opens a feedback window; its layouts, themes and shortcuts are part of that window, and the manage_logs.py commands are a separate script, not MCP tools.
Requires
- uv on PATH
- Python 3.10+
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
Clone the project
TERMINAL
git clone https://github.com/zengxiaolou/interactive-feedback-mcp.git
cd interactive-feedback-mcpCheck that the server starts
TERMINAL
uv run server.pyMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_INTERACTIVE_FEEDBACK_MCP>",
"run",
"server.py"
],
"timeout": 600,
"autoApprove": [
"interactive_feedback"
]
}
}
}Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"interactive-feedback": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_INTERACTIVE_FEEDBACK_MCP>",
"run",
"server.py"
],
"timeout": 600
}
}
}
