Caution

74/100

7 days ago

computer-use-plus

Item: computer-use-plus
Rating: 74
Author: M8ven

MCP server for Windows computer use, providing low-token, low-latency automation through UIA/Win32, OCR, and vision. It enables batch actions, shortcuts, isolated desktop execution, and browser control via MCP tools.

→ Ethanout/computer-use-plus · listed on glama

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

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 push why connect →

Who stands behind it

Ethanout

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

Glama

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings

⚠️

Tests do not pass

Either the test suite is broken or the code regressed. Either way the published behaviour can’t be verified by the publisher’s own tests.

✅

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 4 credentials: COMPUTER_USE_PLUS_AI_API_KEY, COMPUTER_USE_PLUS_FAST_API_KEY, COMPUTER_USE_PLUS_HTTP_TOKEN, COMPUTER_USE_PLUS_VISION_API_KEY

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// 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_PLUS_ACTION_CLASSIFIER_THRESHOLD

configCOMPUTER_USE_PLUS_AGENT_ALLOWED_WINDOWS$env:='[{"process":"qq"}]'

🔐 secretCOMPUTER_USE_PLUS_AI_API_KEY

configCOMPUTER_USE_PLUS_AI_BASE_URL$env:='https://api.openai.com/v1'

configCOMPUTER_USE_PLUS_AI_KEY_FILE$env:='C:\path\to\provider-key.txt'

configCOMPUTER_USE_PLUS_AI_MODEL$env:='gpt-4o-mini'

configCOMPUTER_USE_PLUS_AI_PROTOCOL

configCOMPUTER_USE_PLUS_AUTO_ORGANIZE

configCOMPUTER_USE_PLUS_BROWSER_EXECUTABLE

configCOMPUTER_USE_PLUS_DATA_DIR本地记忆、隔离代理和运行日志默认写入项目下的 .data/，可通过指定目录。Windows 默认启用 backgroundOnly：computer.state、computer.inspect 和 computer.act 都只操作专用执行桌面。仅调试旧的前台模式时可设置 COMPUTER_USE_PLUS_EXECUTION_MODE=foregroundAllowed。

configCOMPUTER_USE_PLUS_EXECUTION_MODE本地记忆、隔离代理和运行日志默认写入项目下的 .data/，可通过 COMPUTER_USE_PLUS_DATA_DIR 指定目录。Windows 默认启用 backgroundOnly：computer.state、computer.inspect 和 computer.act 都只操作专用执行桌面。仅调试旧的前台模式时可设置 =foregroundAllowed。

🔐 secretCOMPUTER_USE_PLUS_FAST_API_KEY

configCOMPUTER_USE_PLUS_FAST_BASE_URL

configCOMPUTER_USE_PLUS_FAST_MODEL

configCOMPUTER_USE_PLUS_FAST_TIMEOUT_MS

configCOMPUTER_USE_PLUS_HTTP_CONNECTIONS

configCOMPUTER_USE_PLUS_HTTP_HOST

configCOMPUTER_USE_PLUS_HTTP_PORT$env:='8765'

🔐 secretCOMPUTER_USE_PLUS_HTTP_TOKEN$env:='replace-with-a-local-token'

configCOMPUTER_USE_PLUS_PYTHON

configCOMPUTER_USE_PLUS_RISK_MODE

configCOMPUTER_USE_PLUS_RISK_POLICY_FILE高风险动作默认需要一次性确认令牌。可通过指向 JSON 策略文件；示例见 [risk-policy.example.json](docs/risk-policy.example.json)。策略可按进程和窗口标题匹配并给出 allow、confirm 或 deny，跨窗口 shortcut 以整条动作链生成确认摘要。

configCOMPUTER_USE_PLUS_TOOL_PROFILE$env:='fast-agent'

configCOMPUTER_USE_PLUS_VERIFY_ROOTS

🔐 secretCOMPUTER_USE_PLUS_VISION_API_KEY

configCOMPUTER_USE_PLUS_VISION_BASE_URL

configCOMPUTER_USE_PLUS_VISION_MODEL

configCOMPUTER_USE_PLUS_VISION_TIMEOUT_MS

// quality suggestions

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

17/17 tools missing one or more hints — agent.run (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agent.status (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); agent.cancel (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +14 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 pass

npm test failed — tests do not pass

Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.

Shell command execution

3 child_process/subprocess calls in production code — runs shell commands (src/media-trimmer.js:22, src/drivers/cdp.js:213, src/drivers/ocr.js:19)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

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/ethanout-computer-use-plus-1kd8sa?variant=verified)](https://m8ven.ai/mcp/ethanout-computer-use-plus-1kd8sa)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: 6689f7b4f75af9446fe1b3509f40934d6475050e

code hash: 8e593460fd1e5a69942e484bb705c9bf9f4e4c92ed0ef4ab1f44f09c9be3ab54

verified: 8/14/2026, 9:51:25 AM

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