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
Beginner mode On
ColoursSystemLightDark
LanguageไทยEnglish中文日本語한국어EspañolDeutsch
☰ MenuSettings
Beginner mode On
ColoursSystemLightDark
LanguageไทยEnglish中文日本語한국어EspañolDeutsch

Minion

by apophisssversion 1.1.1i★ –iRuns on your computer
Registry nameio.github.Apophisss/minion

Install

Overview

Description from the maker (original English)

Featherweight Linux desktops for AI agents: read the screen as text, click, type, run any app.

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: Developer tools

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.

You need

  • npmNode.js installed (for the npx command)

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

claude mcp add minion -- npx -y minion-desktop mcp

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "minion": {
      "command": "npx",
      "args": [
        "-y",
        "minion-desktop",
        "mcp"
      ]
    }
  }
}

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.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "minion": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "minion-desktop",
        "mcp"
      ]
    }
  }
}

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 8, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account apophisss, 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 Developer toolsi

  • More stars than 0% of the other 4926 servers in this category
  • Published to the registry more recently than 64% of the other 4926 servers in this category
  • Basic checks equal to or better than 100% of the other 4926 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 Minion 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 (1.1.1) reached the registry 22 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv), Node.js, MCPB on your computer.

What can I use instead?

In the same category: GitHub, Desktop Commander, Cloudflare MCP

Alternatives

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

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

GitHub

GitHub’s official server lets AI read and manage code, issues and pull requests in your account. Use GitHub’s hosted version or run it locally with Docker.

by githubWidely used★ 34.2KUpdated 5 days ago

Computer or cloud
Install

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 709.6K/wk★ 10.2KUpdated 17 days ago

Runs on your computer
Install

Cloudflare MCP

Cloudflare MCP servers

by cloudflareGrowing★ 4.4KUpdated 14 months ago

Runs in the cloud✓ mcp.cloudflare.com
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.

Give every AI agent its own computer.

Featherweight Linux desktops (office, dev, research, browser, data, Windows apps) that any agent can use:

Claude, ChatGPT, Gemini, Cursor, VS Code, LangChain, your own code, or a model running on your laptop.

Agents read the screen as text, act in batches or in code, and use any program or website.

English · 简体中文 · 繁體中文 · 한국어 · 日本語 · עברית

Get started

All you need is Docker (or OrbStack or Podman). Then pick one:

1. One click in your AI app:

Claude Code: claude plugin marketplace add apophisss/minion && claude plugin install minion@minion. Any other MCP client: uvx minion-desktop mcp, or npx -y minion-desktop mcp. The buttons, uvx and npx start Minion with uv (npx can use pipx instead); the Claude Desktop extension needs nothing else.

2. One line that installs Minion and connects every AI app on your computer (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf/Devin, Gemini CLI, Codex, LM Studio, Cline, Kiro):

curl -fsSL https://raw.githubusercontent.com/apophisss/minion/main/install.sh | sh        # macOS, Linux
irm https://raw.githubusercontent.com/apophisss/minion/main/install.ps1 | iex             # Windows

It ends with minion setup, which checks Docker, prepares a desktop and runs minion connect. Run either one again any time.

3. From ChatGPT, Claude.ai or Le Chat in the browser: run minion share and paste the URL it prints into the app's connector settings (how).

Then just ask: *"Create an office desktop, write a one-page brief about our Q3 numbers in Writer and save it as brief.docx."* Every way to install is in docs/install.md.

▶ Watch the one-minute demo : an agent researches a trip on Wikipedia, makes a budget with a chart and writes the plan as a PDF. 12 tool calls and 2,372 tokens of text; the same steps with screenshots would cost about 36,855. Recorded live with python scripts/demo_video.py , which makes the calls an agent would make.

Why Minion

  • 🖥️ Any program, any website. Every desktop is a real Linux computer: browsers, LibreOffice, IDEs, terminals, file dialogs and installers, plus Windows programs through the windows (Wine) profile. Open any app by name and it is installed the first time (open gimp, open vscode, open dbeaver, any Debian package), web apps open in the browser (open gmail), and the first open answers with a few tips for the app. 130+ apps by name.
  • 🧭 Shortcuts through every app. see --menus lists every menu command with its keyboard shortcut, and menu "File > Export as PDF" runs one without opening a menu. path ~/out.pdf fills any Open/Save dialog. Right-click menus show up in see, button:Save picks one kind of control, and a button below the fold is scrolled into view. Any document reads as text (read report.docx, xlsx with formulas, pptx, pdf) and converts in one call (convert report.docx pdf).
  • 🧠 Agents read the screen as text. see turns any window into a list of controls with stable `@ids`, taken from the accessibility tree with OCR as a fallback: @12 button "Save" (210,62). Web pages, editors (with line numbers), terminals, dropdowns with their options, and spreadsheets (row by row: row 2: A2 North · B2 120) all come out as exact text. When pixels matter, screenshots can draw the @ids for you.
  • 🎯 Honest actions. Every action waits for the screen to settle (for web pages to load, and while an app says "Loading…") and reports what happened: windows, a page's alert or prompt, files saved or downloaded, a pop-up that took the click. Text targets must really be on screen: a miss fails with the closest candidates instead of clicking something else. Tested on 93 everyday tasks done by AI agents.
  • 🪙 Built to save tokens. You get diffs instead of re-reads (see(changes=true): about 80 tokens instead of about 900). Code mode runs a 50-step GUI loop in one call, crops and half-size screenshots cut image cost, a compact mode shrinks the tool definitions from about 3,300 tokens to 450, and the Agent Skill costs about 100 tokens until it is used.
  • 🪶 Featherweight. One small container per desktop (Xvfb, a 2-process window manager and taskbar, a small agent), with no VNC and no desktop environment. Desktops are ready in about 1.5 s and use about 60 MB when idle. Idle desktops are frozen automatically (0% CPU) and wake in about 0.2 s.
  • 🔌 Works with every agent. One toolset everywhere: MCP (local or remote), function calling for OpenAI, Anthropic, Gemini and local models, HTTP with OpenAPI, a CLI and an Agent Skill for shell agents, Python and TypeScript SDKs, and native adapters for Claude, OpenAI and Gemini computer use.
  • ⚡ Parallel by design. create count=8 starts a desktop per worker, fork clones one before a risky step, and sessions keep agents apart.
  • 🙋 Humans in the loop. A live view in the browser offers one-click *take control*, moves files both ways (drop them on the screen) and shares the clipboard. Agents can hand off ("please sign in") and wait for *Done*, and a sign-in saved once by hand starts new desktops signed in.
  • 🎞️ Teach once, replay forever. Every action is recorded. Export an HTML timeline or GIF, or turn the session into a Python script that replays it with no model at all.
  • 📦 Zero dependencies. The host side is pure Python standard library. Desktops run in Docker or Podman (macOS, Windows, Linux), or natively on Linux.

A quick tour from the shell

Any agent with a terminal (Claude Code, Codex CLI, Aider, Open Interpreter, Goose) can use the CLI directly, and minion skill --install teaches it how:

minion up research

minion open en.wikipedia.org # waits until the page has loaded minion fill "Search Wikipedia" "Ada Lovelace" && minion key Return minion wait-for "Analytical Engine" # says where it saw the text minion see --full # read the article as text minion select @14 "Title" # pick a dropdown option minion shot -o page.png --marks # a screenshot with @ids drawn on it minion read ~/Downloads/paper.pdf # any document as text: pdf, docx, xlsx, pptx, epub... minion open gimp # any app by name: installed the first time minion menu "File > Export As > Export as PDF..." # any menu command minion path ~/Documents/report.pdf # fill the open Save/Open dialog minion cp :~/Documents/notes.md . # copy files out (and in)

Menus, file dialogs and apps by name: menu "File > Export As > Export Directly as PDF" , path ~/Documents/report.pdf , then open gimp , which installed GIMP in 16 s. Recorded by the flight recorder.

Works with every agent

Your agentConnect with
Claude Desktop/Code, Cursor, VS Code, Codex, Gemini CLI, opencode, OpenClaw, Windsurf/Devin, LM Studio, Kiro, Gooseone click, minion connect, or uvx minion-desktop mcp (install)
Agent frameworks: OpenAI Agents SDK, LangChain/LangGraph, LlamaIndex, CrewAI, smolagents, Pydantic AI, Google ADK, AutoGenthe same MCP server (verified recipes)
ChatGPT, Claude.ai, Le Chat (web apps)minion share: remote MCP over HTTPS (docs)
Any model with function calling (OpenAI, Anthropic, Gemini, Mistral, local models via Ollama/vLLM)`Toolkit().definitions("openai" \"anthropic" \"gemini") + Toolkit().run_calls()` (docs)
Anything that speaks HTTP (n8n, Dify, GPT Actions, any language)minion serve → /api/tools/*, /mcp and /openapi.json (docs)
Shell agentsthe minion CLI (docs) and its Agent Skill (minion skill --install)
Python / TypeScript codefrom minion import Desktop (docs) · clients/typescript
Native computer-use modelsClaude toolset (docs) · OpenAI and Gemini computer use (docs)

A complete agent with any OpenAI-compatible model ("anthropic", "gemini" and "openai-responses" work the same way):

from openai import OpenAI

from minion.tools import Toolkit

tk = Toolkit() client = OpenAI() # or OpenAI(base_url="http://localhost:11434/v1", api_key="ollama") for a

Only the beginning is shown; read the rest in the repo

Ask PopNx