CUA MCP Server (duvoai/cua-mcp-server) is an MCP server listed on the M8ven Trust Index. It scores 60 out of 100, grade C. It declares 9 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
60/100

CUA MCP Server

Enables autonomous desktop automation by delegating tasks to vision-based agents operating within cloud-based virtual machine sandboxes. It allows users to manage VMs, execute complex computer tasks, and receive text-based screen summaries across Linux, Windows, and macOS environments.

→ duvoai/cua-mcp-server· 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

⚡ 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

duvoai

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
⚠️
Known vulnerabilities in dependencies: 3 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
✅
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
🔐
You'll be asked for 2 credentials: ANTHROPIC_API_KEY, CUA_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes9 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.

list_sandboxes

List all CUA cloud sandboxes with their current status

get_sandbox

Get details of a specific sandbox including API URLs

start_sandbox

Start a stopped sandbox

stop_sandbox

Stop a running sandbox

restart_sandbox

Restart a sandbox

describe_screen

Get a text description of current screen state using vision AI. No actions taken. Use for situational awareness without running a full task. Images are processed server-side and never returned.

run_task

Execute a computer task autonomously. The MCP server will control the sandbox, take screenshots, and complete the task using vision AI. Only the result summary is returned - no images. Use this for any desktop automation task.

get_task_history

Retrieve the result of a previously executed task. Use the history_url from run_task response for fastest lookup.

get_task_progress

Check the progress of a running task. Returns current step, last action, and status. For completed tasks, includes the final result. Poll this every 5-10 seconds during long-running tasks.

// known CVEs in dependencies3 high

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.23.0GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.23.0GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.23.0GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// 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.
🔐 secretANTHROPIC_API_KEYYes
configCUA_API_BASECustom API base URL (default: https://api.cua.ai) No
🔐 secretCUA_API_KEYYes
configCUA_MODELModel to use: claude-opus-4-5 (default) or claude-sonnet-4-5 No
// 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

9/9 tools missing one or more hints — list_sandboxes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_sandbox (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); start_sandbox (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 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.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Production dependencies are patched

0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.23.0 (high), @modelcontextprotocol/sdk@1.23.0 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

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 5 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/duvoai/cua-mcp-server?variant=verified)](https://m8ven.ai/mcp/duvoai/cua-mcp-server)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 7fd2769e6dc10401b75bd1629b53759527950cc4
code hash: ce2cef606bb808533a7ab7a7e3ed2170b7c65454f8ab7f5c832a6b1d0dcc11aa
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