MCP Feedback Enhanced

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL

https://heyclau.de/entry/mcp/mcp-feedback-enhanced

Source URLs

https://github.com/Minidoracat/mcp-feedback-enhanced/blob/main/README.md, https://github.com/Minidoracat/mcp-feedback-enhanced

Brand

MCP Feedback Enhanced

Brand domain

github.com

Safety notes

The server is designed to interrupt agent workflows for human feedback, but MCP client settings such as auto-approval can still let the tool launch without a fresh prompt., Version notes describe auto command execution for preset commands after sessions or commits; review and disable command presets unless they are intentional and safe., Keep `MCP_WEB_HOST` set to `127.0.0.1` unless remote access is required and protected by the surrounding development environment., Image upload, clipboard paste, desktop notifications, audio notifications, and session export can make feedback sessions more powerful but also easier to misuse on shared machines., Do not use feedback prompts as the only approval barrier for destructive file edits, shell commands, deployments, account changes, or data exfiltration-prone tasks.

Privacy notes

Feedback text, AI work summaries, uploaded images, screenshots, prompt presets, session history, statistics, and exported records may include source code, paths, secrets, customer data, or personal information., WebSocket traffic between the MCP server and feedback UI carries the feedback session data., The README describes local file storage for session history and settings; review retention and export behavior before using it with confidential projects., If the web UI is bound beyond localhost for SSH or remote development, anyone with network access to that interface may be able to view or influence feedback sessions unless the environment adds protection.

Author

Minidoracat

Submitted by

oktofeesh1

Claim status

unclaimed

Last verified

2026-06-06

• Feedback text, AI work summaries, uploaded images, screenshots, prompt presets, session history, statistics, and exported records may include source code, paths, secrets, customer data, or personal information.
• WebSocket traffic between the MCP server and feedback UI carries the feedback session data.
• The README describes local file storage for session history and settings; review retention and export behavior before using it with confidential projects.
• If the web UI is bound beyond localhost for SSH or remote development, anyone with network access to that interface may be able to view or influence feedback sessions unless the environment adds protection.

• Python 3.11 or newer with uv/uvx available.
• MCP client such as Claude, Cursor, Cline, Windsurf, Augment, Trae, or another compatible host.
• Browser access for Web UI mode, or a supported Windows, macOS, or Linux desktop environment for Tauri desktop mode.
• Decision on whether the feedback server should stay local-only or bind to a wider interface for SSH/remote development.
• Review of prompt presets, auto-submit timers, auto command execution settings, and session retention before using it in sensitive projects.

Show that MCP Feedback Enhanced is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

[![Listed on HeyClaude](https://heyclau.de/badge/mcp/mcp-feedback-enhanced.svg)](https://heyclau.de/entry/mcp/mcp-feedback-enhanced)

MCP Feedback Enhanced side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field	MCP Feedback Enhanced Interactive feedback MCP server that opens a web or Tauri desktop interface so AI coding agents can ask the human for confirmation, structured feedback, screenshots, prompt snippets, and follow-up direction during development. Open dossier	Claude Desktop MCP Setup Configure MCP servers in the Claude Desktop app by editing claude_desktop_config.json. Grounded walkthrough covering config file locations, the mcpServers JSON structure, the filesystem server, and how to verify and troubleshoot the connection. Open dossier	Cupertino MCP Server Local Apple documentation CLI and MCP server that gives Claude searchable offline access to Apple Developer Documentation, Swift Evolution proposals, Human Interface Guidelines, sample code, Swift.org pages, the Swift Book, and Swift package metadata. Open dossier	Desktop Commander MCP Server Local MCP server that gives AI assistants terminal control, process management, filesystem operations, search, diff editing, and document handling for desktop automation and development workflows. Open dossier
Next steps	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing	Open dossierCopy installCopy configAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust	Review first	Trusted	Review first	Review first
Review status	Not reviewed	Not reviewed	Not reviewed	Not reviewed
Package trustDiffers	Package not verified	Package verified	Package not verified	Package not verified
Source provenanceDiffers	Source-backed	No submission link	Source-backed	Source-backed
SubmitterDiffers	oktofeesh1	—	oktofeesh1	oktofeesh1
Install risk	Review first	Review first	Review first	Review first
Notes	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓	Safety ✓ Privacy ✓
Brand	—	Anthropic	—	Desktop Commander
Category	mcp	mcp	mcp	mcp
Source	Source-backed	First-party	Source-backed	Source-backed
Author	Minidoracat	JSONbored	mihaelamj	wonderwhy-er
Added	2026-06-06	2025-10-27	2026-06-06	2026-06-05
Platforms	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Harness	Claude CodeCodexCursorClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop	Claude CodeClaude Desktop
Source repo	—	—	—	—
Safety notes	✓The server is designed to interrupt agent workflows for human feedback, but MCP client settings such as auto-approval can still let the tool launch without a fresh prompt. Version notes describe auto command execution for preset commands after sessions or commits; review and disable command presets unless they are intentional and safe. Keep `MCP_WEB_HOST` set to `127.0.0.1` unless remote access is required and protected by the surrounding development environment. Image upload, clipboard paste, desktop notifications, audio notifications, and session export can make feedback sessions more powerful but also easier to misuse on shared machines. Do not use feedback prompts as the only approval barrier for destructive file edits, shell commands, deployments, account changes, or data exfiltration-prone tasks.	✓Local MCP servers run as processes on your machine with your user account's privileges, so they can perform any file or system operation you can. Only add servers you trust, and restrict filesystem server paths to the minimum directories the workflow needs. Each Claude Desktop tool call (file write, delete, move) requires your explicit approval before it executes; review every request before approving.	✓Cupertino is an independent third-party project, not an official Apple project. The setup flow downloads a large local documentation bundle; review available disk space and cache locations before installing on managed machines. Self-building or refreshing the corpus can crawl Apple documentation and related public sources; respect Apple site terms and internal network policies. Codex users should pass `serve --no-reap` because upstream documents Codex process spawning behavior that can otherwise close the transport during tool calls. Documentation answers can be stale or incomplete after Apple platform releases, so verify compatibility-sensitive API, beta, and deprecation guidance against live Apple documentation before shipping code.	✓Desktop Commander can run shell commands, stream process output, start and stop processes, read and write files, edit documents, search directories, and change local configuration. The project's security policy describes built-in restrictions as guardrails rather than hardened security boundaries. Directory restrictions and command blocklists may be bypassed through terminal access, symlinks, absolute paths, or command substitution. Use Docker with selective folder mounts when stronger isolation is required. Review file edits, command execution, process termination, and document rewrites before letting an agent act on important systems.
Privacy notes	✓Feedback text, AI work summaries, uploaded images, screenshots, prompt presets, session history, statistics, and exported records may include source code, paths, secrets, customer data, or personal information. WebSocket traffic between the MCP server and feedback UI carries the feedback session data. The README describes local file storage for session history and settings; review retention and export behavior before using it with confidential projects. If the web UI is bound beyond localhost for SSH or remote development, anyone with network access to that interface may be able to view or influence feedback sessions unless the environment adds protection.	✓Configured servers receive the prompts, file contents, and directory data needed to run their tools, and may store credentials (API keys, tokens) passed through the env block. The claude_desktop_config.json file holds server commands, file paths, and environment-variable names; keep it private and do not commit it to public repositories.	✓Cupertino serves local public documentation over stdio, but prompts and tool results can still expose app architecture, API choices, platform targets, package interests, and sample-code queries to the MCP client, model provider, and logs. The server writes operational output to stderr and uses structured logging; avoid including proprietary source code, unreleased product names, customer data, private bundle identifiers, or internal roadmap details in documentation prompts. Local databases and bundle paths may reveal the developer's Apple-platform focus or package interests to anyone with access to the machine or MCP client logs.	✓Local files, terminal output, environment-derived paths, process listings, command arguments, audit logs, spreadsheets, PDFs, DOCX files, and source code may be exposed to the MCP client and model. Tool logs can contain secrets, customer data, credentials, private repository paths, database output, and internal documents. If using remote AI clients or the project's remote MCP option, review where prompts, tool calls, and file content are transmitted and retained.
Prerequisites	Python 3.11 or newer with uv/uvx available. MCP client such as Claude, Cursor, Cline, Windsurf, Augment, Trae, or another compatible host. Browser access for Web UI mode, or a supported Windows, macOS, or Linux desktop environment for Tauri desktop mode. Decision on whether the feedback server should stay local-only or bind to a wider interface for SSH/remote development.	Claude Desktop installed and running (macOS, Windows, or Linux) Basic JSON knowledge - understand JSON syntax, objects, arrays, and key-value pairs Text editor with JSON syntax highlighting (VS Code, Sublime Text, or similar) Node.js 18+ installed for running npx commands and MCP server packages	macOS with Cupertino's current upstream-supported binary or build toolchain. Homebrew or a manual install path for the Cupertino binary. Approximately 4.2 GB of free disk space for the full pre-built documentation bundle. Network access for the initial database download, or time to crawl and index the documentation sources yourself.	Node.js for the npx installation path, or Docker for the isolated installation path. Claude Desktop or another MCP client that can launch local stdio servers. Clear list of directories, commands, and long-running processes an assistant may access. Backups or version control for files the agent may edit.
Install	uvx mcp-feedback-enhanced@latest Copy install	node --version Copy install	brew tap mihaelamj/tap && brew install cupertino && cupertino setup Copy install	npx @wonderwhy-er/desktop-commander@latest setup Copy install
Config	{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ["mcp-feedback-enhanced@latest"], "timeout": 600, "env": { "MCP_DESKTOP_MODE": "false", "MCP_WEB_HOST": "127.0.0.1", "MCP_WEB_PORT": "8765", "MCP_DEBUG": "false", "MCP_LANGUAGE": "en" } } } } Copy config	Edit via Settings > Developer > Edit Config, then restart Claude Desktop: { "mcpServers": { "filesystem": { "command": "npx", "args": [ "-y", "@modelcontextprotocol/server-filesystem", "/Users/username/Desktop" ] } } } Copy config	{ "mcpServers": { "cupertino": { "command": "/opt/homebrew/bin/cupertino", "args": [ "serve" ], "type": "stdio" } } } Copy config	{ "mcpServers": { "desktop-commander": { "command": "npx", "args": ["-y", "@wonderwhy-er/desktop-commander@latest"] } } } Copy config
Citations	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationmodelcontextprotocol.io Package (SHA-256 pinned)/downloads/mcp/desktop-mcp-setup.mcpb Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-06 Source methodology →	Source repositorygithub.com 2026-07-21T07:17:01+00:00 Documentationgithub.com Submitted by oktofeesh12026-06-05 Source methodology →
Claim	Unclaimed	Unclaimed	Unclaimed	Unclaimed

Source-backed guides for putting this to work.