Labsco
liaosiqian logo

Interactive Feedback MCP

★ 1

from liaosiqian

Provides interactive user feedback and command execution for AI-assisted development.

🔥🔥🔥✓ VerifiedFreeQuick setup
#git

⌁ labsco summary — our analysis, not the vendor's

What it is — an MCP server that adds a human-in-the-loop feedback GUI to AI dev tools like Cursor, letting you run commands, see output, and reply to the AI mid-task.

What you get —

  • A Qt GUI with quick-response buttons (e.g. "Looks good," "Needs minor tweak," "Do all checklist items")
  • RIPER-5 workflow buttons (Research → Innovate → Plan → Execute → Review)
  • Cross-platform command execution with live output, auto-execute mode, and per-project command history
  • Image drag-drop / Ctrl+V paste with compression and Base64 for AI image recognition

Requirements — nothing — runs out of the box; no API keys (settings stored locally via Qt QSettings). Needs a Qt/Python environment.

Cost snapshot — free and MIT-licensed; no paid service. The README argues it saves money by cutting redundant tool calls on platforms like Cursor.

Setup effort — run the MCP server and add the suggested prompt rules to your assistant; a Qt GUI launches on invocation.

Our take — a smart way to reduce expensive speculative tool calls and keep a human at decision points, but the primary docs are Chinese and it depends on a Qt desktop GUI.

Source: the project README — summarized 2026-07-08.