Warning

16/100

11 days ago

open-computer-use

Item: open-computer-use
Rating: 16
Author: M8ven

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents. Self-hosted, open-source, pluggable into any model.

→ Wide-Moat/open-computer-use · listed on github_code

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 push why connect →

Who stands behind it

Wide-Moat

Source: github_code · also listed on github_topic, 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

GitHub GitHub Glama

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

// key findings

🚨

Reads files from sensitive locations

Touches: ~/.config/libreoffice/4/user/basic/Standard

🚨

Code appears obfuscated

5 files are unreadable to a human reviewer. Cannot audit what they do.

🔐

You'll be asked for 9 credentials: MCP_API_KEY, MCP_TOKENS_API_KEY, API_KEY, ANTHROPIC_AUTH_TOKEN, OPENAI_API_KEY, AZURE_OPENAI_API_KEY, OPENROUTER_API_KEY, ANTHROPIC_API_KEY, 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.

configSINGLE_USER_MODEtrue = one container, no chat ID needed; false = require X-Chat-Id; unset = lenient

configCOMMAND_TIMEOUT120 Bash tool timeout (seconds)

configSUBAGENT_CLI

🔐 secretMCP_API_KEYBearer token for MCP endpoint

configBASE_DATA_DIR

🔐 secretMCP_TOKENS_API_KEYSettings Wrapper auth key

🔐 secretAPI_KEY

configSKILLS_DIR

configCONFIG_PATH

config_PATCH_TARGET_OVERRIDE

configOPENCODE_MODEL_ALIASES

configCLAUDE_SUB_AGENT_DEFAULT_MODEL

configCODEX_SUB_AGENT_DEFAULT_MODEL

configCODEX_MODEL

configOPENCODE_SUB_AGENT_DEFAULT_MODEL

configOPENCODE_MODEL

configDOCKER_SOCKET

configDOCKER_IMAGEopen-computer-use:latest Sandbox container image

configCONTAINER_MEM_LIMIT

configCONTAINER_CPU_LIMIT

configENABLE_NETWORK

configPUBLIC_BASE_URLdocker exec computer-use-server env grep ^=

configCONTAINER_IDLE_TIMEOUT

configORCHESTRATOR_CONTAINER_NAME

configMCP_TOKENS_URLSettings Wrapper URL (optional, see below)

configSUB_AGENT_MAX_TURNS

configSUB_AGENT_TIMEOUT3600 Sub-agent timeout (seconds)

🔐 secretANTHROPIC_AUTH_TOKENAnthropic key (for Claude Code sub-agent)

configANTHROPIC_BASE_URL

configANTHROPIC_MODEL

configANTHROPIC_DEFAULT_SONNET_MODEL

configANTHROPIC_DEFAULT_OPUS_MODEL

configANTHROPIC_DEFAULT_HAIKU_MODEL

configCLAUDE_CODE_SUBAGENT_MODEL

configCLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS

configDISABLE_PROMPT_CACHING

configDISABLE_PROMPT_CACHING_SONNET

configDISABLE_PROMPT_CACHING_OPUS

configDISABLE_PROMPT_CACHING_HAIKU

🔐 secretOPENAI_API_KEYEdit .env — set (or any OpenAI-compatible provider)

configOPENAI_BASE_URL

🔐 secretAZURE_OPENAI_API_KEY

configAZURE_OPENAI_ENDPOINT

configAZURE_OPENAI_API_VERSION

configCODEX_CONFIG_EXTRA

🔐 secretOPENROUTER_API_KEY

🔐 secretANTHROPIC_API_KEY

configOPENCODE_CONFIG_EXTRA

🔐 secretVISION_API_KEYVision API key (for describe-image)

configVISION_API_URL

configVISION_MODEL

configSKILLS_CACHE_DIR

configSKILLS_CACHE_HOST_PATH

// quality suggestions

Dependencies

21 dependencies, 1 flagged: playwright

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

5/5 tools missing one or more hints — bash_tool (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); str_replace (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); create_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +2 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.

No access to sensitive paths

Reads sensitive paths: ~/.config/libreoffice/4/user/basic/Standard

Remove reads of sensitive system paths. If you genuinely need them, document why in the README.

No eval / new Function

4 eval() or new Function() calls — dynamic code execution

Replace eval / Function with explicit parsing or safer alternatives.

Shell command execution

69 child_process calls — runs shell commands

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

Readable source code

5 files appear obfuscated

Ship unminified, readable source.

Dependency freshness

5/21 production deps abandoned (no release in 2+ years): pdf-lib@2022-05-12 (4.2y), graphviz@2022-06-18 (4.1y), markdown-pdf@2022-07-12 (4.1y)

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 7 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/wide-moat-open-computer-use-8litwr?variant=verified)](https://m8ven.ai/mcp/wide-moat-open-computer-use-8litwr)

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

commit: a0d0ba28b4a7d5c477310c2d8ad0716829e728de

code hash: bff0f565af0f56ff7e5ca89d5919616b5a1533bb8e8fbe713295adf618b6f7ac

verified: 8/8/2026, 7:41:40 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