Camoufox (baixianger) MCP Server
camoufox-mcp
npm
v1.0.0
Published by baixianger — 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.
MCP server for Camoufox browser automation with anti-detection capabilities
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 8
high Tool "evaluate_mainworld" exposes command/code executionMTC-CAP-001
Tool "evaluate_mainworld" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool evaluate_mainworld
high Tool "evaluate_isolated" exposes command/code executionMTC-CAP-001
Tool "evaluate_isolated" appears to run shell commands or evaluate code (parameter "script"). Arbitrary execution driven by model input is one of the most dangerous MCP capabilities; combined with any untrusted input it becomes RCE.
Fix: Sandbox execution, allowlist commands/arguments, and never pass model output to a shell unescaped.
Location: tool evaluate_isolated
high Shell/command execution in server code (dist/browser/installer.js)MTC-SRC-002
In the server's implementation (`dist/browser/installer.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: import { spawn } from 'child_process'; import { existsSync, readdirSync } from 'fs'; import { join } from 'path'; impor
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/browser/installer.js
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([get_page_text]) co-exist with external-action tools ([evaluate_mainworld, evaluate_isolated]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [get_page_text] → sinks [evaluate_mainworld, evaluate_isolated]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow get_page_text → evaluate_mainworld
medium Unconstrained command parameter "script" on "evaluate_mainworld"MTC-CAP-006
Tool "evaluate_mainworld" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool evaluate_mainworld · inputSchema.properties.script
medium Unconstrained command parameter "script" on "evaluate_isolated"MTC-CAP-006
Tool "evaluate_isolated" takes a command-shaped parameter "script" with no enum/pattern constraint. Free-form, model- or attacker-controlled arguments reaching a shell is the command-injection precondition.
Fix: Constrain the parameter (enum/pattern), or build the command from a fixed template with escaped args.
Location: tool evaluate_isolated · inputSchema.properties.script
low Mutating tool "evaluate_mainworld" declares no destructiveHintMTC-CAP-005
Tool "evaluate_mainworld" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool evaluate_mainworld
low Mutating tool "evaluate_isolated" declares no destructiveHintMTC-CAP-005
Tool "evaluate_isolated" can mutate/egress but declares no destructiveHint. Clients that don't default to spec-safe behavior may not prompt before running it.
Fix: Declare accurate annotations, and gate destructive tools on user confirmation regardless.
Location: tool evaluate_isolated
Tools 42
Each tool and what it can reach — statically extracted from the published source.
evaluate_isolatedruns code / shellevaluate_mainworldruns code / shellget_page_textingests untrusted inputclear_console_logsno sensitive capabilityclear_network_logsno sensitive capabilityclickno sensitive capabilityclose_pageno sensitive capabilityclose_sessionno sensitive capabilitycreate_sessionno sensitive capabilitydismiss_popupsno sensitive capability
Show 32 more tools ↓
dragno sensitive capabilityfillno sensitive capabilityfill_formno sensitive capabilityget_config_pathsno sensitive capabilityget_console_logsno sensitive capabilityget_framework_stateno sensitive capabilityget_network_logsno sensitive capabilityget_recording_statusno sensitive capabilityhoverno sensitive capabilityinit_user_configno sensitive capabilityinject_contextno sensitive capabilityintercept_networkno sensitive capabilitylist_context_filesno sensitive capabilitylist_pagesno sensitive capabilitylist_sessionsno sensitive capabilitynavigate_pageno sensitive capabilitynew_pageno sensitive capabilitypress_keyno sensitive capabilityreload_settingsno sensitive capabilityremove_interceptno sensitive capabilitysave_sessionno sensitive capabilityselect_pageno sensitive capabilitystart_console_captureno sensitive capabilitystart_network_captureno sensitive capabilitystart_recordingno sensitive capabilitystop_console_captureno sensitive capabilitystop_network_captureno sensitive capabilitystop_recordingno sensitive capabilitytake_screenshotno sensitive capabilitytake_snapshotno sensitive capabilitywait_forno sensitive capabilitywait_for_navigationno 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 (42 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 |
|---|---|---|---|---|
v1.0.0 latest |
A 93/100 | 8 | 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 camoufox-mcp --onlineOther implementations of Camoufox 5
Independent packages implementing the same tool, scanned with the same engine. Compare all 6 side by side →
MCP server for browser automation using Camoufox - a privacy-focused Firefox fork with advanced anti-detection features
Browser automation server backed by the Camoufox browser.
MCP server for browser automation with Camoufox anti-detection capabilities
Browser automation MCP server that does not get blocked, backed by Camoufox anti-detect Firefox
MCP server for stealth browser automation via Camoufox — 79 tools, Chrome DevTools MCP-level power with anti-bot stealth
More in Browser Automation
Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.
Screenshot any URL or HTML as PNG/JPEG/WebP from your AI agent. Full-page, clean, no install.
MCP server for aria51 accessibility scanner
Bridge any browser web app to Claude Code via MCP
Browserbase’s official MCP server: cloud headless browsers for agents, with sessions and screenshots.
MCP server for AI web browser automation using Browserbase and Stagehand