Wmux MCP Server
@wong2kim/wmux
npm
v2.0.8
Published by @wong2kim — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.
Windows terminal multiplexer with MCP server for AI agents - run multiple CLI sessions in parallel, control via Claude Code and other AI tools
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −1.2 | Package runs install-time scripts MTC-SUP-010 | supply-chain |
2. Client adoption risk — 99 − 7 = 92. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −1 | publisher verification (public source) — no provenance, but the source is public and inspectable |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 3
high Dynamic code execution in server code (dist/mcp/mcp/playwright/security.js)MTC-SRC-001
In the server's implementation (`dist/mcp/mcp/playwright/security.js:15`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: \s+Function\b/, label: 'new Function()' }, { pattern: /\bdocument\.cookie\b/, label: 'document.cookie access' },
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/mcp/mcp/playwright/security.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([browser_download, browser_wait_for_download]) co-exist with external-action tools ([browser_file_upload]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [browser_download, browser_wait_for_download] → sinks [browser_file_upload]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow browser_download → browser_file_upload
low Package runs install-time scripts (postinstall)MTC-SUP-010
"@wong2kim/wmux" executes postinstall script(s) at install time. An install hook runs at install time; most are routine build/setup, but review what it does before trusting it.
Evidence: node scripts/fix-node-pty.js
Fix: Review the scripts; install with --ignore-scripts where possible and vet what they do.
Location: package @wong2kim/wmux
Tools 44
Each tool and what it can reach — statically extracted from the published source.
browser_downloadingests untrusted inputbrowser_file_uploadnetwork egressbrowser_wait_for_downloadingests untrusted inputbrowser_clickno sensitive capabilitybrowser_closeno sensitive capabilitybrowser_consoleno sensitive capabilitybrowser_cookiesno sensitive capabilitybrowser_dialogno sensitive capabilitybrowser_dragno sensitive capabilitybrowser_emulateno sensitive capability
Show 34 more tools ↓
browser_evaluateno sensitive capabilitybrowser_extract_datano sensitive capabilitybrowser_extract_textno sensitive capabilitybrowser_fillno sensitive capabilitybrowser_highlightno sensitive capabilitybrowser_hoverno sensitive capabilitybrowser_navigateno sensitive capabilitybrowser_navigate_backno sensitive capabilitybrowser_networkno sensitive capabilitybrowser_openno sensitive capabilitybrowser_pdfno sensitive capabilitybrowser_press_keyno sensitive capabilitybrowser_resizeno sensitive capabilitybrowser_response_bodyno sensitive capabilitybrowser_screenshotno sensitive capabilitybrowser_scroll_into_viewno sensitive capabilitybrowser_selectno sensitive capabilitybrowser_session_listno sensitive capabilitybrowser_session_startno sensitive capabilitybrowser_session_statusno sensitive capabilitybrowser_session_stopno sensitive capabilitybrowser_smart_snapshotno sensitive capabilitybrowser_snapshotno sensitive capabilitybrowser_storageno sensitive capabilitybrowser_tabsno sensitive capabilitybrowser_traceno sensitive capabilitybrowser_typeno sensitive capabilitybrowser_waitno sensitive capabilitypane_listno sensitive capabilitysurface_listno sensitive capabilityterminal_readno sensitive capabilityterminal_sendno sensitive capabilityterminal_send_keyno sensitive capabilityworkspace_listno sensitive capability
Toxic flows 1
Cross-tool combinations that form a data-exfiltration primitive (untrusted input → sensitive source → external sink).
What this scan could not see
- Tools were statically extracted from the published source (44 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v2.0.8 latest |
A 92/100 | 3 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @wong2kim/wmux --onlineMore in Developer Tools
Hotel booking MCP server — 300K+ properties, real confirmation numbers, loyalty programs. Builders monetize every booking via Stripe Connect. The first MCP server that completes real hotel reservations inside AI conversations.
Manage AdGuard Home through AI assistants
Read-only Azure DevOps for MCP clients using only your existing browser session — no PAT, no Azure CLI. Browse work items, pull requests, comments, attachments and Artifacts feeds across every project, repo and feed you can access.
MCP server for Adobe Experience Manager Assets integration development
Servidor MCP para el tiempo oficial de España (API pública OpenData de AEMET). Predicción, observación y avisos como herramientas MCP tipadas.
A standalone MCP stdio bridge for Affinity by Canva's local MCP SSE server.