Minion
MCPB · MINION.MCPB · 3 COMPONENTS
Featherweight Linux desktops for AI agents: read the screen as text, click, type, run any app.
Available components
Last scanned (9 hours ago)
Scores higher than 76% of MCPB servers
Category Browser Automation
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. How we score → Why this is hard to score →
Supply Chain Security0
- No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.Unverified
- Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
- Install-script risk not yet assessed.Unverified
- Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).Unverified
Provenance & Transparency39
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Build provenance not yet verified. View diagnostics → Unverified
- Clear OSI-approved license (MIT).Pass
- Maintenance history not yet determined.Unverified
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability55
- AI-judged instruction clarity (good).Pass
- 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. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management67
- Stability observed for 20 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage95
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 84% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Checks we ran (9)
- Source repository
- License
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (7)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Malware scan in Supply Chain Security (scores 0 for this)No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
- Known CVEs in Supply Chain Security (scores 0 for this)Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- Install scripts in Supply Chain Security (scores 0 for this)Install-script risk not yet assessed.
- Dependency health in Supply Chain Security (scores 0 for this)Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- Provenance in Provenance & TransparencyBuild provenance not yet verified.
- Maintenance in Provenance & TransparencyMaintenance history not yet determined.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −1
- Provenance: fail → unverified ▼ security
- Maintenance: pass → unverified ▼ functional
- Security disclosure: pass → unverified ▼ functional
- 3 Nov 26 +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.
- 1 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 30 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 28 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 24 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.
- 22 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed mcpb/https://github.com/Apophisss/minion/releases/download/v1.1.1/minion.mcpb@1.1.1
Provenance Inconclusive
We could not complete the check, so nothing is claimed either way. This is a gap on our side, not a finding about the package.
| Result | Inconclusive |
|---|---|
| Ecosystem | mcpb |
| Reason | Check deferred |
Background: How many MCP packages publish verified provenance →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
act ~495
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.
| Name | Type | Req | Description |
|---|---|---|---|
| actions | array | yes | – |
| 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… |
No output schema declared.
No examples provided.
desktop ~330
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).
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| 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. |
No output schema declared.
No examples provided.
files ~309
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 ~.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | – |
| 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 | yes | 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. |
No output schema declared.
No examples provided.
open ~170
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.
| Name | Type | Req | Description |
|---|---|---|---|
| desktop | string | – | Desktop name (default: the one you created or used last). |
| install | boolean | – | Install a missing app first (default true). |
| target | string | yes | – |
No output schema declared.
No examples provided.
run ~125
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.
| Name | Type | Req | Description |
|---|---|---|---|
| background | boolean | – | – |
| command | string | yes | – |
| desktop | string | – | Desktop name (default: the one you created or used last). |
| timeout | number | – | Seconds (default 120). |
No output schema declared.
No examples provided.
screenshot ~162
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
script ~215
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.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | Python source. |
| desktop | string | – | Desktop name (default: the one you created or used last). |
| timeout | number | – | Seconds (default 120). |
No output schema declared.
No examples provided.
see ~243
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.
| Name | Type | Req | Description |
|---|---|---|---|
| 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. |
No output schema declared.
No examples provided.
view ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| desktop | string | – | Desktop name (default: the one you created or used last). |
| message | string | – | – |
| timeout | number | – | Seconds to wait for the human (default 600). |
No output schema declared.
No examples provided.
How do I install the Minion MCP server?
Minion ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, f94496d1fe282de55c59ece58b9edb58d3685cf67c7961a3e82339418a45a557; the commands to do that are on this page. If it does not match, do not open it.
mcpb · minion.mcpb
Download bundleCheck the download matches the SHA-256 the MCP registry declares before you open it. If it does not match, do not open the file.
SHA-256
f94496d1fe282de55c59ece58b9edb58d3685cf67c7961a3e82339418a45a557
macOS / Linux
echo "f94496d1fe282de55c59ece58b9edb58d3685cf67c7961a3e82339418a45a557 minion.mcpb" | shasum -a 256 -c
Windows (PowerShell)
(Get-FileHash -Algorithm SHA256 .\minion.mcpb).Hash -eq "f94496d1fe282de55c59ece58b9edb58d3685cf67c7961a3e82339418a45a557"
Run it in the folder you saved the bundle to, then open the file with an MCPB-capable host such as Claude Desktop.
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 MCPB bundle (https://github.com/Apophisss/minion/releases/download/v1.1.1/minion.mcpb).
Is the Minion MCP server safe to use?
Minion scores 45 out of 100 on VerifyMCP. 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.
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 9 checks on Minion, covering Source repository, License, Schema quality, Stability and 5 more. 7 items could not be completed, a gap on our side rather than a finding about Minion: Malware scan, Known CVEs, Install scripts, Dependency health and 3 more. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an MCPB bundle, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.