guarded-computer-use-mcp (be1st6666/guarded-computer-use-mcp) is an MCP server listed on the M8ven Trust Index. It scores 70 out of 100, grade C. It declares 26 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
70/100

guarded-computer-use-mcp

Windows computer-use MCP server (26 tools) with a human-in-the-loop approval gate: physical-input-only dialogs, signed guard switches, deny/launch lists, hash-chained audit log. 70+ unit tests, green CI.

→ be1st6666/guarded-computer-use-mcp· listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

be1st6666

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
⚠️
Tool annotations don’t match behaviour
1 read-only tool performs write/delete/exec — ocr (line 756: (await import('node:fs/promises')).unlink(shot.path))
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
✅
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: COMPUTER_USE_GUARD_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes26 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

screenshot
zoom

Capture a small region at native resolution — use this to read fine detail such as UI labels or icons.

screen_hash
wait_for_change
batch
bench

Time each stage of the screenshot pipeline across encoding/scale variants. Diagnostic only.

cursor_position

Current mouse cursor position in physical pixels.

list_displays

All monitors with their bounds in the virtual desktop coordinate space.

list_windows

All visible top-level windows with title, pid, minimized state and rect.

active_window

The foreground window (handle, pid, process name, title, rect).

clipboard_read

Read the clipboard as text.

mouse_move

Move the cursor to (x, y) without clicking.

click

Click at (x, y), or at the current cursor position when x/y are omitted. count=2 for a double click.

drag

Press at (x1, y1), move to (x2, y2), release. The move is interpolated in steps for reliability.

scroll

Scroll the wheel at (x, y) (moves the cursor there first when given). amount is in wheel notches.

type_text
key

Press a key or chord, e.g. "enter", "esc", "f5", "ctrl+c", "ctrl+shift+s", "alt+f4", "win+d".

hold_key

Hold a key down for a duration (ms), e.g. to charge or repeat.

activate_window
ocr
find_elements
click_element
ui_tree
launch_app
clipboard_write

Put text on the clipboard. Useful when typing into an app that mangles direct input.

wait

Sleep for a number of milliseconds — use between an action and the screenshot that verifies it.

// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configCOMPUTER_USE_AUDIT
configCOMPUTER_USE_AUDIT_MAX_BYTES
configCOMPUTER_USE_AUDIT_REDACT_TITLES
configCOMPUTER_USE_AUDIT_STDERR
configCOMPUTER_USE_GUARD_ALLOW_PLAIN
🔐 secretCOMPUTER_USE_GUARD_SECRETThe markers are signed with guard.key (or in the
configCOMPUTER_USE_OCR_IDLE_MS
configCOMPUTER_USE_POLICY
configCOMPUTER_USE_SHELL
configCOMPUTER_USE_UV
configProgramFiles
configProgramFiles(x86)
configSystemRoot
// quality suggestions

Tool annotations match behaviour

1 read-only tool performs write/delete/exec — ocr (line 756: (await import('node:fs/promises')).unlink(shot.path))

Either remove the readOnlyHint:true annotation, or remove the write/delete call from the tool handler.

Destructive tools are labelled

1 tool perform destructive updates without destructiveHint — ocr deletes at line 756 ((await import('node:fs/promises')).unlink(shot.path))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/be1st6666/guarded-computer-use-mcp?variant=verified)](https://m8ven.ai/mcp/be1st6666/guarded-computer-use-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 5cbcfde03d1676cb747506a4ad06a884ec4d3bc6
code hash: d2d432892188147f6f2d2775b957c89a418d7f49accf8a552838283f788af60b
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client