open-cowork (OpenCoworkAI/open-cowork) is an MCP server listed on the M8ven Trust Index. It scores 42 out of 100, grade D. It declares 28 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
D
Caution
42/100

open-cowork

Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integration.

→ OpenCoworkAI/open-cowork· 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

OpenCoworkAI

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
🚨
Secret credentials may flow to a network call
2 flows detected: ANTHROPIC_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
⚠️
Known vulnerabilities in dependencies: 8 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 4 credentials: ANTHROPIC_API_KEY, ANTHROPIC_AUTH_TOKEN, GEMINI_API_KEY, OPENAI_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// known CVEs in dependencies8 high3 medium6 low

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

high@mariozechner/pi-coding-agent@0.60.0GHSA-jfgx-wxx8-mp94

Pi Agent: Predictable temporary extension install paths allow local privilege escalation on shared Linux hosts

highngrok@5.0.0-beta.2GHSA-qr28-p3wr-mxq3

ngrok is Vulnerable to Command Injection

highws@8.19.0GHSA-96hv-2xvq-fx4p

ws: Memory exhaustion DoS from tiny fragments and data chunks

highelectron@41.7.1GHSA-9f4c-93c8-jc8g

Electron: Sandboxed iframe can bypass the allow-popups restriction via the OpenURL navigation path

highpostcss@8.5.14GHSA-r28c-9q8g-f849

PostCSS: Path Traversal in Previous Source Map Auto-Loading (sourceMappingURL) leads to Arbitrary .map File Disclosure

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.
configAGENT_CLI_PATH
🔐 secretANTHROPIC_API_KEY
🔐 secretANTHROPIC_AUTH_TOKEN
configANTHROPIC_BASE_URL
configANTHROPIC_DEFAULT_SONNET_MODEL
configCLAUDE_MODEL
configCOMSPEC
configCONDA_PREFIX
configCOWORK_WORKDIR
configDEFAULT_CWD
🔐 secretGEMINI_API_KEY
configGEMINI_BASE_URL
configOPENAI_ACCOUNT_ID
🔐 secretOPENAI_API_KEY
configOPENAI_API_MODE
configOPENAI_BASE_URL
configOPENAI_MODEL
configOPEN_COWORK_CLICLICK_PATH
configOPEN_COWORK_DISABLE_IMAGE_TOOL_OUTPUT
configOPEN_COWORK_PYTHON_HOME
configOPEN_COWORK_PYTHON_PATH
configOPEN_COWORK_RESOURCES_PATH
configPROGRAMFILES
configPROGRAMFILES(X86)
configSHELL
configSystemRoot
configVITE_DEV_SERVER_URL
configWORKDIR
configWORKSPACE_DIR
// 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

28/28 tools missing one or more hints — get_displays (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); click (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); type_text (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +25 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.

Tool test coverage

Only 5/28 tools referenced in tests (18%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

3 calls in production code run through a shell (src/main/mcp/software-dev-server-example.ts:457, src/main/skills/plugin-runtime-service.ts:307, src/main/skills/plugin-runtime-service.ts:319)

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

Secrets stay with their owner

2 secrets sent to a request target we could not resolve (ANTHROPIC_API_KEY → dynamic, ANTHROPIC_API_KEY → dynamic) — often a configured endpoint, not necessarily third-party

Audit where credentials are sent. A NOTION_TOKEN should only reach api.notion.com — never a third-party host.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Production dependencies are patched

0 critical, 3 high severity in production deps — @mariozechner/pi-coding-agent@0.60.0 (high), ngrok@5.0.0-beta.2 (high)

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

Dev dependencies

5 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

3/35 production deps abandoned (no release in 2+ years): rehype-sanitize@2023-11-20 (2.8y), remark-math@2023-11-20 (2.8y), rehype-katex@2024-08-19 (2.1y)

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 8 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/opencoworkai/open-cowork?variant=verified)](https://m8ven.ai/mcp/opencoworkai/open-cowork)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a1d0e4ab0f0f78bc42c622653174650cd2025968
code hash: a7e135d8b896cd19fa61c147dd732cdf92e184c94c8dce3e951a8fa15cb87ef2
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