interactive_feedbackLABSCO SUMMARY
One question to you costs less than five speculative tool calls.
The pitch is concrete: by asking rather than branching into guesses, a stretch that would have taken up to 25 tool calls collapses into a single feedback-aware request — which on a metered platform is money as well as time.
What it is
A single-purpose server that opens a desktop window for human-in-the-loop review. The assistant calls it instead of guessing or instead of declaring a task finished, and waits for what you type.
What you get
- One tool,
interactive_feedback, taking aproject_directoryand asummaryof what the assistant just did, and returning your typed reply - A command box in the same window: run something, see its output, and let that inform the feedback you send back
- Per-project settings kept in Qt's
QSettings— the command to run, whether to execute it automatically on the next start for that project, and whether the command section is shown - A "Save Configuration" button for the current command and the auto-run checkbox; the command section's visibility saves the moment you toggle it
Requirements
Python 3.11 or newer and uv. Clone the repository, run uv sync, then start it with uv run server.py. In the client config, point command at uv with --directory set to your clone; the documented example sets a timeout of 600 and auto-approves interactive_feedback. Settings are stored in the platform's usual place — the registry on Windows, plist files on macOS, ~/.config or ~/.local/share on Linux — under organization FabioFerreira and application InteractiveFeedbackMCP. Compatible with Cursor, Cline and Windsurf.
Setup effort
Build from source — git clone https://github.com/noopstudios/interactive-feedback-mcp.git
USE CASES
01
Stopping the assistant before it guesses
Add a rule telling it to call the feedback tool whenever it would otherwise ask a question, and it waits for you instead of picking an interpretation and running with it.
02
Reviewing work before it is called done
Have it call the tool instead of ending the request, and keep calling until your feedback is empty — so "finished" is your word, not its.
03
Checking the change actually runs
Set the project's command once, tick "Execute automatically on next run", and the output is already on screen when the window opens.
04
Keeping premium request counts down
On platforms that meter tool invocations, a check-in that consolidates a long speculative chain into one round trip is the cheapest correction available.
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.
Requires
- uv on PATH
- Python 3.11 or later
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
Install uv — Linux/Mac: curl -LsSf https://astral.sh/uv/install.sh | sh ; Windows: pip install uv
TERMINAL
git clone https://github.com/noopstudios/interactive-feedback-mcp.git
cd interactive-feedback-mcp
uv syncMCP Clients
Cursor
CURSOR · JSON
{
"mcpServers": {
"interactive-feedback-mcp": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_INTERACTIVE_FEEDBACK_MCP>",
"run",
"server.py"
],
"timeout": 600,
"autoApprove": [
"interactive_feedback"
]
}
}
}<YOUR_PATH_TO_INTERACTIVE_FEEDBACK_MCP> is the full path of your clone.
