Prototype · Preview: every server in the official registry, synced every 30 minutes. Reviews and accounts come in a later step.
PopNx MCPMCP servers for people who use AI · explained in plain words

Feedbacks

by Softinator-TechLabsversion 0.2.3i★ –iRuns on your computer
Registry nameio.github.Softinator-TechLabs/feedbacks

Install

Overview

Description from the maker (original English)

Visual website feedback, screenshots and team discussion for coding assistants. Self-hosted.

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

  • Connection: Runs on your computer
  • Transport: stdio
  • Category: Other

Install

Pick the AI app you use, then copy the settings.

Before you install

  • Basic checks: 1 of 1 passed
  • Runs on your computer with your user’s permissions (files, network, apps).
  • The registry lists no key to fill in.

Which app do you use?

Pick your app above. We remember it, so next time the button says “Install in …”.

Download the maker’s .mcpb file

The link goes to the maker’s own file; we do not host or repackage it. Open the file and Claude Desktop installs it.

Run this in your terminal

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account Softinator-TechLabs, which owns the repo

  • … Not checked yet

    Still maintained

    We have not read this repo from GitHub yet

  • … Not checked yet

    Has a licence

    We have not read this repo from GitHub yet

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Compared with others in Otheri

  • More stars than 0% of the other 32384 servers in this category
  • Published to the registry more recently than 69% of the other 32384 servers in this category
  • Basic checks equal to or better than 100% of the other 32384 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Feedbacks safe?

It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed –, and the latest version (0.2.3) reached the registry 16 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need MCPB on your computer.

What can I use instead?

In the same category: Spec Driven Development, Remote Desktop Commander, 오늘냥이 (Oneul Nyangi)

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Spec Driven Development

by formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

Runs on your computer★ 440MITUpdated 14 months ago
Install

Remote Desktop Commander

by desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

Runs in the cloud★ 211Updated yesterday
Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Feedbacks

Free, Apache-2.0 visual feedback, session replay and debugging context.

Show the problem with a screenshot, exact text suggestion or video + session recording. Keep the discussion, event timeline, browser diagnostics and approved project context together. Your team and coding agent can investigate the evidence, make the agreed change and record verification. The complete product is free to self-host; you provide the infrastructure and any AI tools you use.

Set up a team server first. The order is: server → install and connect the Chrome extension → project context, optional GitHub App and members → each developer's personal MCP setup. One installation serves your team; the extension does not host a server. Follow the complete setup flow, or the separate DevOps installation guide.

Website · Why Feedbacks · Self-hosting · Extension · Coding assistants & plugins · API & MCP · Roadmap · Contributing

What it does

  • Show exactly what changed: screenshot pins, annotation, full-page capture and selected-text replacement suggestions.
  • Replay the bug: video or session-only recording with one timeline for activity, console, network and performance. Save and annotate frames.
  • Take the evidence: complete thread bundles with discussion, media, recordings, diagnostics and checksums; scoped agent reads and recording exports.
  • Give agents context: approved project instructions, reviewer guidance and responsibilities through MCP, API and CLI.
  • Move the work forward: assignments, categories, tags, saved views and point progress; optional GitHub Issues across repositories and installations, with multiple configured Apps and one owner-selected App per project.
  • Review beyond the extension: scoped guest links, PDF/image review, an optional text widget, surveys/NPS, scheduled public-page QA, native mobile clients and signed webhooks.
  • Own the whole service: Apache-2.0 server and clients, PostgreSQL and private S3-compatible storage. One installation serves one organization.

Recording guide · Debug bundles · Text suggestions · More review workflows

Feedbacks is an early 0.x release. Each application deployment serves one organization. Public registration, billing, SSO and shared-database customer tenancy are not implemented. See architecture and deployment boundaries.

Try it with Docker

curl -fsSL https://feedbacks.softinator.ai/install.sh | bash

Open http://localhost:3000 with the generated owner login. PostgreSQL and screenshots persist in Docker volumes; no S3 account or source build is required. The installer requires Docker Compose, Bash, curl and OpenSSL, and preserves existing installation directories. See the quickstart and production guide.

Develop from source

Requirements: Node.js 22 or 24, npm, and Docker Compose for PostgreSQL.

git clone https://github.com/Softinator-TechLabs/feedbacks-oss.git

cd feedbacks-oss npm ci cp .env.example .env docker compose -f compose.dev.yaml up -d --wait npm run bootstrap npm run build npm run dev:server

Before bootstrap, add BOOTSTRAP_EMAIL, BOOTSTRAP_NAME and a unique BOOTSTRAP_PASSWORD to your local .env. Bootstrap creates the first owner once. Remove the bootstrap password afterward. Open localhost:3000. The example database password is for the loopback-only development database.

For live client edits, run npm run dev:web in another terminal and set APP_ORIGIN=http://localhost:5173 in .env before restarting the server. Use that origin in the browser. For the standalone public website, use npm run dev:site.

Production requires HTTPS, PostgreSQL and private S3-compatible storage. Follow the deployment guide for configuration, first-owner setup and recovery.

For a registry deployment, use the public Docker Hub image and registry Compose. The illustrated storage guide maps the five prerequisites to their environment fields. Developers can install the bundled Claude Code and Codex plugins in two commands, then connect their own scoped key.

Plugin directory status

Checked 21 October 2026. Direct Claude Code and Codex installation is available from our public marketplace.

Official directoryCurrent status
Claude CodeVersion 0.2.2 passed its security scan. Publication was requested and is waiting for an Anthropic reviewer; it is not live in the official directory.
OpenAILocal command/stdio MCP submission access is pending OpenAI review. Official directory submission and publication are not yet available for this package.

These reviews have no confirmed publication date. Use the direct installation instructions today; directory status does not change the self-hosted Apache-2.0 product. See agent setup and distribution boundaries.

Browser extension

Build with npm run build:extension. Load the dist/extension/unpacked/ directory from Chrome's Load unpacked, or use the ZIP in dist/extension/. Enter your own Feedbacks server address and approve pairing in the web application. Website-wide permission is a separate optional action. Existing saved server connections remain available.

Repository map

PathResponsibility
src/server/Authentication, project access, business operations, persistence and transports
src/shared/Typed operation inputs, outputs and descriptions
src/web/Authenticated React application
src/cli/Bootstrap, JSON CLI and stdio MCP adapter
plugins/Codex and Claude Code plugin packages and review skills; MCP bundles generated at build
extension/Chrome Manifest V3 capture and review extension
site/Independently deployable public website
tests/Isolated authorization, transport and database tests
ops/Generic deployment configuration
docs/Public contributor and operator documentation

Agent development

Start with AGENTS.md and the documentation map. Claude Code and Gemini CLI have thin adapters to the same instructions. See supported skills and client setup. For an isolated app with synthetic data and no deployment credentials:

npm ci

npm run harness:dev

The command builds the app and prints its loopback URL and private local access-file path. Each run has a disposable database and independent port.

Development

npm run check

Optional native PostgreSQL concurrency tests (initdb and pg_ctl on PATH):

npm run test:postgres

check runs formatting, architecture/docs checks, type checking, tests, all builds, an isolated app smoke check and release-content checks. CI also runs the native PostgreSQL tests, dependency audit and secret scanning. A passing build is not evidence of production deployment or capacity.

License and community

The application, extension and website source are Apache-2.0 licensed. Dependencies retain their licenses. Read contribution guidelines, community standards, security reporting and trademark guidance.

Ask PopNx