Arc Browser (Mukbeast4) MCP Server
arc-browser-mcp
npm
v0.2.3
Published by mukbeast4 — 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.
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 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 7 = 93. 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 4
high Shell/command execution in server code (dist/engines/cdp/launcher.js)MTC-SRC-002
In the server's implementation (`dist/engines/cdp/launcher.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: , execSync } from "node:child_process"; import { mkdirSync } from "node:fs"; import { log } from "../../lib/log.js"; con
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/engines/cdp/launcher.js
high Shell/command execution in server code (dist/engines/live/osascript.js)MTC-SRC-002
In the server's implementation (`dist/engines/live/osascript.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { log } from "../../lib/log.js"; export function runAppleScript(script, t
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/engines/live/osascript.js
high Shell/command execution in server code (dist/engines/live/screenshot.js)MTC-SRC-002
In the server's implementation (`dist/engines/live/screenshot.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { readFile, unlink } from "node:fs/promises"; import { tmpdir } from "nod
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/engines/live/screenshot.js
high Shell/command execution in server code (dist/lib/arcProcess.js)MTC-SRC-002
In the server's implementation (`dist/lib/arcProcess.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; export function parsePsOutput(stdout) { const procs = []; for (const raw
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/lib/arcProcess.js
Tools 40
Each tool and what it can reach — statically extracted from the published source.
arc_upload_filenetwork egressarc_active_stateno sensitive capabilityarc_cdp_startno sensitive capabilityarc_cdp_stopno sensitive capabilityarc_check_capabilitiesno sensitive capabilityarc_clickno sensitive capabilityarc_close_tabno sensitive capabilityarc_dragno sensitive capabilityarc_emulateno sensitive capabilityarc_evaluateno sensitive capability
Show 30 more tools ↓
arc_fillno sensitive capabilityarc_fill_formno sensitive capabilityarc_focus_spaceno sensitive capabilityarc_get_console_messageno sensitive capabilityarc_get_network_requestno sensitive capabilityarc_get_textno sensitive capabilityarc_go_backno sensitive capabilityarc_go_forwardno sensitive capabilityarc_handle_dialogno sensitive capabilityarc_hoverno sensitive capabilityarc_list_console_messagesno sensitive capabilityarc_list_network_requestsno sensitive capabilityarc_list_spacesno sensitive capabilityarc_list_tabsno sensitive capabilityarc_list_windowsno sensitive capabilityarc_little_arcno sensitive capabilityarc_navigateno sensitive capabilityarc_open_tabno sensitive capabilityarc_performance_start_traceno sensitive capabilityarc_performance_stop_traceno sensitive capabilityarc_press_keyno sensitive capabilityarc_reloadno sensitive capabilityarc_resize_pageno sensitive capabilityarc_screenshotno sensitive capabilityarc_select_tabno sensitive capabilityarc_snapshotno sensitive capabilityarc_statusno sensitive capabilityarc_take_heap_snapshotno sensitive capabilityarc_typeno sensitive capabilityarc_wait_forno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (40 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 |
|---|---|---|---|---|
v0.2.3 latest |
A 93/100 | 4 | 1.9.0 | 2026-07-24 |
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 arc-browser-mcp --onlineOther implementations of Arc Browser 1
Independent packages implementing the same tool, scanned with the same engine. Compare all 2 side by side →
More in Browser Automation
Security scan results for the Agentql MCP server.
Security scan results for the Aria51 MCP server.
Security scan results for the Bifrost MCP server.
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
Security scan results for the Browserbase MCP server.
Security scan results for the Camoufox MCP server.