Minidoracat/mcp-feedback-enhanced

Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.

What it solves

This project provides a way to insert human checkpoints into long-running AI tasks. It prevents AI agents from making speculative operations or drifting from the user's intent by requiring the AI to confirm actions with the user through an interactive interface before proceeding.

How it works

It is an MCP (Model Context Protocol) server that triggers a Web UI or a Desktop Application when the AI calls a specific tool. The AI sends a request for feedback, and the user provides input via the interface (text, prompt selection, or image uploads). This feedback is delivered back to the AI in real-time via a WebSocket connection, allowing the AI to adjust its behavior or continue the task based on the human response.

Who it’s for

Developers using MCP-compatible AI IDEs and agents (such as Cursor, Cline, Windsurf, Augment, and Trae) who want more control over autonomous AI workflows, especially in local, SSH remote, or WSL environments.

Highlights

  • Dual Interface Options: Supports both a lightweight Web UI and a cross-platform Desktop Application (Tauri-based).
  • Smart Interaction: Includes prompt management for common responses, auto-timed submission, and support for image uploads (PNG, JPG, GIF, etc.).
  • Environment Adaptability: Specifically designed to work across local, SSH remote, and WSL environments with automatic detection.
  • Session Tracking: Automatically records session history and statistics with export options for JSON, CSV, and Markdown.
  • Rich Media Support: Renders AI work summaries in Markdown and supports clipboard pasting for images.

Related

  • Project
    blazickjp/arxiv-mcp-server

    A local MCP server for agent literature work. The differentiator is original-LaTeX section reads, BibTeX from arXiv metadata, and topic watches. Papers stay on disk. The working loop is paper ID → outline → one section → citations. Search is optional.

  • Project
    opentokenz/mcpx

    MCPX is a local runtime gateway for the Model Context Protocol that provides AI agents with secure, stateful, and auditable access to local development environments, files, and terminal tasks.

  • Project
    Claude-Reverser/IDA-instances-MCP

    A fork of ida‑pro‑mcp that provides a hardened, multi‑instance MCP server for headless IDA Pro, enabling AI agents (Claude Code, etc.) to drive reverse‑engineering tasks via a secure HTTP API.

  • Project
    apify/mcpc

    mcpc is a universal command‑line client for the Model Context Protocol (MCP). It maps every MCP operation—tools, prompts, resources, tasks, skills, OAuth authentication, and even experimental x402 payments—into intuitive shell commands. Designed for AI agents and developers, it lets you inspect, debug, and script MCP workflows using standard Unix tools (e.g., jq, xargs). Features include persistent named sessions, progressive tool discovery via `grep`, JSON‑only output mode, secure OAuth 2.1 storage (OS keychain or protected file), AI sandboxing, and lightweight cross‑platform support.

  • Project
    anysearch-ai/anysearch-mcp-server

    AnySearch MCP Server is a real‑time, HTTP‑based MCP endpoint that lets LLM‑powered agents perform general web search, vertical‑domain search, parallel batch queries, and full‑page content extraction. It works with an optional API key (higher limits) or anonymously (lower limits) and provides ready‑made configuration snippets for all major AI‑coding assistants (OpenCode, Claude Code, Cursor, VS Code, Cline, Codex, Antigravity, DeepSeek Harness, Hermes Agent, OMP).