linux-computer-use (Roadmvn/linux-computer-use) is an MCP server listed on the M8ven Trust Index. It scores 28 out of 100, grade F. It declares 21 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
F
Warning
28/100

linux-computer-use

MCP server enabling AI agents to control a real Linux browser with live view, human takeover, and safety guardrails.

→ Roadmvn/linux-computer-use· listed on glama

Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code 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

Roadmvn

Source: Glama

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

Glamanot scored here

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
🚨
Code appears obfuscated
1 file are unreadable to a human reviewer. Cannot audit what they do.
// tools this server exposes21 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.

open

Open a browser session, or attach to a browser already running with a CDP endpoint. Call this first.

goto

Navigate the current tab to a URL.

snapshot

Accessibility tree of the page with a ref for each element. Use these refs with click and fill. Prefer this over screenshot for acting: it is exact and cheap.

screenshot

Image of the page. Use it to read visual content, verify a result, or work out coordinates for the mouse tool.

click

Click an element by its ref from snapshot. Blocked when the element looks irreversible unless confirm is true.

type

Type text into the focused element. Refused when a password field has focus.

fill

Fill a field identified by its ref. Refused on credential fields.

press

Press a key, for example Enter, Tab or ArrowDown.

mouse

Coordinate based mouse control for canvas, maps and custom widgets that have no accessible element. Take a screenshot first to read the coordinates.

tabs

List, open, select or close tabs.

history

Go back, go forward or reload.

status

Report the session, the mode and who holds the control lease. Pass takeover: true to hand control to the human before they act in the dashboard. Control comes back only when the human releases it on their machine, never through this tool.

set_mode

normal asks before sensitive actions. auto runs a complete objective end to end, stopping only for an empty login, an account choice, or an irreversible action.

desktop_start

Start the agent desktop, a nested X display in a resizable window. Required before any other desktop tool. Pass stop: true to shut it down.

desktop_windows

List the visible windows on the agent desktop, with id, title, class and geometry.

desktop_focus

Bring a window of the agent desktop to the front. Keyboard input goes to the focused window.

desktop_screenshot

Capture the agent desktop, or a single window of it. Use it to find coordinates before clicking.

desktop_click

Move the pointer of the agent desktop and click. Coordinates come from desktop_screenshot.

desktop_type

Type text into the focused window of the agent desktop. Typing into a terminal needs confirm, because a shell runs whatever it receives.

desktop_key

Press a key or combination on the agent desktop, for example Return, ctrl+c or alt+Tab.

desktop_launch

Start an application on the agent desktop, found by name in the desktop catalog. Applications outside the allowed list need confirm.

// 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.
configDISPLAYA graphical session: or WAYLAND_DISPLAY set for the MCP client. No screen, wrap it in xvfb-run.
configLCU_APPS
configLCU_DATA_DIR
configLCU_IRREVERSIBLE
configLCU_PLAYWRIGHT_CLI
// quality suggestions

Dependencies

2 runtime dependencies, 1 flagged: @playwright/cli

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

21/21 tools missing one or more hints — open (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); goto (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); snapshot (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +18 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Tests exist

No test files found

Add tests that exercise each declared tool.

Readable source code

1 file appear obfuscated, including code that decodes and evaluates itself at runtime

Ship unminified, readable source.

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 4 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/roadmvn/linux-computer-use?variant=verified)](https://m8ven.ai/mcp/roadmvn/linux-computer-use)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: df36e5ce069de8ccbf5f3ea4a6c94b7a0bbe778f
code hash: 86417d96c7f7ed97a08d03f65965441c724963587be4fc96d9b353960ed9e909
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