# Minion (pypi · minion-desktop)

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

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `minion.mcpb`: 45/100, [markdown](https://verifymcp.io/servers/apophisss-minion/minion.md), [page](https://verifymcp.io/servers/apophisss-minion/minion)
- npm · `minion-desktop`: 40/100, [markdown](https://verifymcp.io/servers/apophisss-minion/minion-desktop.md), [page](https://verifymcp.io/servers/apophisss-minion/minion-desktop)
- pypi · `minion-desktop`: 87/100 (this document), [markdown](https://verifymcp.io/servers/apophisss-minion/minion-desktop-2.md), [page](https://verifymcp.io/servers/apophisss-minion/minion-desktop-2)

## Channel facts

- Registry: `pypi`
- Package: `minion-desktop`
- Version: `1.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Apophisss/minion).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 19 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2592 tokens (~288/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 67/100
  - Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 84% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Minion MCP server?

Minion runs locally as a PyPI package, launched with uvx minion-desktop mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add apophisss-minion -- uvx minion-desktop mcp
```

### Cursor

```json
{
  "mcpServers": {
    "apophisss-minion": {
      "command": "uvx",
      "args": [
        "minion-desktop",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "apophisss-minion": {
      "command": "uvx",
      "args": [
        "minion-desktop",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add apophisss-minion -- uvx minion-desktop mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "apophisss-minion": {
      "type": "local",
      "command": [
        "uvx",
        "minion-desktop",
        "mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add apophisss-minion --command uvx --arg minion-desktop --arg mcp
```

### Hermes

```yaml
mcp_servers:
  apophisss-minion:
    command: "uvx"
    args: ["minion-desktop", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "apophisss-minion": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "minion-desktop",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add apophisss-minion -t stdio -c uvx -a minion-desktop mcp
```

### Other

```json
{
  "mcpServers": {
    "apophisss-minion": {
      "command": "uvx",
      "args": [
        "minion-desktop",
        "mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 87, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 69, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-29 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `desktop` (~330 tokens)

Create and manage Linux desktops (isolated computers with GUI apps). Actions: create (profile, name, size, count for several at once), list, profiles, remove, freeze (0% CPU; any later call wakes it), thaw, fork (clone disk state into a new desktop to try something risky), snapshot, restore, replay (HTML timeline of everything done), macro (the actions so far as a Python script that replays them with the script tool, no model needed), logins (sign-ins the human saved: create with login=NAME starts signed in). Profiles: browser (Firefox, blocks ads and cookie banners), office (LibreOffice + Firefox), dev (git, Python, Node.js, Chromium, IDE), research (Firefox + PDF/notes tools), data (office + pandas/matplotlib), windows (Windows .exe/.msi programs via Wine, x86-64 hosts), base (minimal).

Input parameters:

- `action` (string, required)
- `count` (integer): create: how many desktops (parallel work). Default 1.
- `desktop` (string): Desktop name (default: the one you created or used last).
- `login` (string): create: start signed in, from a sign-in the human saved.
- `name` (string): create/fork: name of the new desktop (optional).
- `profile` (string): Profile for create (default: browser).
- `size` (string): Screen for create: 1280x800 (default), 1024x768 cheaper.
- `tag` (string): Snapshot tag for snapshot/restore.

### `see` (~243 tokens)

Read the screen as text: windows, then the focused window's UI elements with stable @ids, roles, names, values, states and center coordinates (accessibility tree). Text that accessibility doesn't have (an app without it, slides, canvases, pictures of text, remote screens) is read with OCR in the screen's language. Exact and far cheaper than a screenshot. changes=true returns only what changed since your last look.

Input parameters:

- `changes` (boolean): Only what changed since your previous see().
- `desktop` (string): Desktop name (default: the one you created or used last).
- `full_text` (boolean): Keep paragraphs whole (to read an article/document).
- `lang` (string): OCR language when the screen's own is wrong: "heb", "ara+eng", "jpn"... (implies ocr)
- `menus` (boolean): Also list the app's menu commands and their keyboard shortcuts (for act menu).
- `ocr` (boolean): Also OCR smaller pictures and, when nothing is missing, the whole window (slower).
- `window` (string): Describe this window (title, app or index) instead.

### `screenshot` (~162 tokens)

Look at the screen (PNG). Image pixels are desktop coordinates unless scaled or cropped (the reply explains the mapping). marks=true draws @ids on clickable elements. detail="low" halves each side (about 4x fewer image tokens). region=[x,y,w,h] crops; zoom=true magnifies the region.

Input parameters:

- `desktop` (string): Desktop name (default: the one you created or used last).
- `detail` (string): low = half size.
- `grid` (boolean): Overlay a labelled 100 px coordinate grid.
- `marks` (boolean): Label clickable elements with their @ids.
- `region` (array): [x, y, width, height].
- `zoom` (boolean): Magnify the region to 1024 px wide.

### `act` (~495 tokens)

Mouse and keyboard. Runs the actions in order, stops at the first failure, waits for the screen to settle and reports what changed. Actions (objects with an `action` field): click | double_click | triple_click (select a line) | right_click | middle_click (target; modifiers "ctrl"), move (target), drag (from, to), type (text; \n = Enter, \t = Tab), paste (text), fill (target, text: replace a field's content), select (target, option: pick a dropdown option by its text), key (keys: "ctrl+s", "Return", or a sequence "Tab Tab Return"; repeat), scroll (direction, amount, target), wait (seconds), wait_for (text, timeout; gone=true), scroll_to (text: brings it into view wherever it is on a long page, loading more of a feed), focus (window), close (window, like its X button), copy (target: its whole text to the clipboard), goto (target: a URL in the browser's current tab), menu (item: a menu path like "File > Export as PDF"; see(menus=true) lists them), path (path: fill the open Open/Save/Export dialog with a full file path and confirm; overwrite=true replaces a file), mouse_down/mouse_up (target: press/release for custom drags), hold_key (keys, seconds). Targets: "@12" from your latest see (best), exact visible text ("Save"; fails if not on screen), a kind and a label ("button:Save", "link:Docs", "field:Email", "tab:Settings"), or "x,y". The reply says what changed: windows, a page's alert/confirm dialog, files saved or downloaded; it waits while the app shows "Loading…". A page may still fill in after a click: wait_for text you expect.

Input parameters:

- `actions` (array, required)
- `desktop` (string): Desktop name (default: the one you created or used last).
- `observe` (string): What to return after acting: auto (default: the summary, plus the changed UI as text when a page, window or dialog changed or the app finished working), summary, changes (+ the changed UI as text), s…

### `open` (~170 tokens)

Open something and wait until its window is ready: an app ("writer", "calc", "firefox", "terminal", or any app by name: "gimp", "inkscape", "vscode", "chrome", "thunderbird", "blender", "dbeaver"... installed the first time, which can take a minute), a web app by name ("gmail", "figma", "google sheets"), a URL ("github.com"), a file in the desktop ("~/Documents/report.docx"), or a shell command. The reply includes short tips for the app the first time.

Input parameters:

- `desktop` (string): Desktop name (default: the one you created or used last).
- `install` (boolean): Install a missing app first (default true).
- `target` (string, required)

### `run` (~125 tokens)

Run a bash command inside the desktop (as the desktop user; sudo works) and get stdout, stderr and the exit code. Best for files, data, git, conversions. Install anything with `minion-install <name or URL>` (apt packages, .deb/.AppImage/archive URLs, pip:pkg, npm:pkg). background=true for servers.

Input parameters:

- `background` (boolean)
- `command` (string, required)
- `desktop` (string): Desktop name (default: the one you created or used last).
- `timeout` (number): Seconds (default 120).

### `script` (~215 tokens)

Run Python inside the desktop to do many GUI steps in one call (loops, retries, data entry): only what it prints comes back. Preloaded: see(changes=False), elements(role, name), find(text), cells() (visible spreadsheet cells {"A1": ...}), click(target), double_click, right_click, write(text), paste(text), key(keys), scroll(dir, n), fill(target, text), drag(a, b), wait(s), wait_for(text, timeout) -> bool, menu("File > Save"), menus(), path(file), read(file) -> text, convert(file, to) -> path, launch(app_or_url), run(cmd) -> dict, windows(), focus(title), scroll_to(text), close(window), copy(target), clipboard(text=None). Targets as in act. Errors raise MinionScriptError.

Input parameters:

- `code` (string, required): Python source.
- `desktop` (string): Desktop name (default: the one you created or used last).
- `timeout` (number): Seconds (default 120).

### `files` (~309 tokens)

Files in a desktop. read: any file as text: text files as they are, documents converted (docx, xlsx with values and formulas, pptx, odt/ods/odp, pdf, epub, html, images by OCR, doc/xls/ppt). convert: path -> another format (to: pdf, docx, xlsx, csv, pptx, png, md, ...; returns the new path). write: text -> path (replaces the file; creates folders). upload: local_path (on the machine running Minion) -> path. download: path -> local_path (never overwrites unless overwrite=true). local_path is limited to Minion's files folder (relative paths start there). Desktop paths may start with ~.

Input parameters:

- `action` (string, required)
- `desktop` (string): Desktop name (default: the one you created or used last).
- `details` (boolean): read: formatting too (shapes' sizes and slide backgrounds, spacing, fonts).
- `local_path` (string): upload/download: path on the machine running Minion (download default: .).
- `overwrite` (boolean): download: replace an existing local file.
- `path` (string, required): Path inside the desktop, e.g. ~/Documents/report.docx.
- `text` (string): write: the whole new content.
- `to` (string): convert: the new format, e.g. pdf, docx, xlsx, csv, png.

### `view` (~99 tokens)

A live link where the human can watch the desktop and take over mouse and keyboard. With message, hand control to the human ("Please sign in to your bank") and wait until they press Done (up to timeout seconds); returns their note.

Input parameters:

- `desktop` (string): Desktop name (default: the one you created or used last).
- `message` (string)
- `timeout` (number): Seconds to wait for the human (default 600).

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/apophisss-minion/minion-desktop-2#diagnostics

## Score history

- 2026-11-05: 87
- 2026-11-04: 71
- 2026-11-03: 71
- 2026-11-02: 70
- 2026-11-01: 70
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 84
- 2026-10-28: 83
- 2026-10-27: 83
- 2026-10-26: 82
- 2026-10-25: 82
- 2026-10-24: 81
- 2026-10-23: 81
- 2026-10-22: 80
- 2026-10-21: 80
- 2026-10-20: 79
- 2026-10-19: 79
- 2026-10-18: 78
- 2026-10-17: 78
- 2026-10-16: 78

## Common questions

### What is the Minion MCP server?

Minion is an MCP server listed in the public MCP registry as io.github.Apophisss/minion. Featherweight Linux desktops for AI agents: read the screen as text, click, type, run any app. This page covers its PyPI package (minion-desktop).

### Is the Minion MCP server safe to use?

Minion scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Minion MCP server expose?

Minion exposes 9 tools: desktop, see, screenshot, act, open, and 4 more. Their descriptions and schemas cost roughly 2,148 tokens of context every time the server is loaded.

### Is the Minion MCP server still maintained?

Minion is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Minion MCP server under?

Minion declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Minion MCP server?

VerifyMCP ran 16 checks on Minion, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/minion-desktop/
- Socket report: https://socket.dev/pypi/package/minion-desktop
- Repository: https://github.com/apophisss/minion
- Website: https://github.com/apophisss/minion/blob/main/docs/install.md
- Changelog RSS feed: https://verifymcp.io/servers/apophisss-minion/minion-desktop-2.xml
- Changelog JSON feed: https://verifymcp.io/servers/apophisss-minion/minion-desktop-2/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/apophisss-minion/minion-desktop-2.json
- HTML version of this page: https://verifymcp.io/servers/apophisss-minion/minion-desktop-2