Ghostvault MCP Server
ghostvault
PyPI
v0.1.1b0
Published by mienetic — 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.
Source-available MCP server for managing browser sessions on any website via Camoufox — sign in, switch accounts, scrape, and automate any login-gated flow through your AI agent.
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 6
high Shell/command execution in server code (src/ghostvault/browser/launcher.py)MTC-SRC-002
In the server's implementation (`src/ghostvault/browser/launcher.py:58`): 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: t. result = subprocess.run( ["system_profiler", "SPDisplaysDataType"], captu
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 src/ghostvault/browser/launcher.py
high Shell/command execution in server code (src/ghostvault/update.py)MTC-SRC-002
In the server's implementation (`src/ghostvault/update.py:67`): 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: try: out = subprocess.run( ["git", *args], cwd=str(cwd), capture_output
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 src/ghostvault/update.py
low Shell/command execution in packaging/dev tooling (examples/scripts/mcp_e2e_test.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`examples/scripts/mcp_e2e_test.py:43`): 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: ult dict.""" proc = subprocess.Popen( [PYTHON, "-m", "ghostvault"], stdin=subprocess.PIPE, s
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 examples/scripts/mcp_e2e_test.py
low Shell/command execution in packaging/dev tooling (examples/scripts/mcp_gmail_test.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`examples/scripts/mcp_gmail_test.py:44`): 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: bprocess.""" proc = subprocess.Popen( [PYTHON, "-m", "ghostvault"], stdin=subprocess.PIPE, s
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 examples/scripts/mcp_gmail_test.py
low Shell/command execution in packaging/dev tooling (examples/scripts/mcp_security_test.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`examples/scripts/mcp_security_test.py:43`): 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: v_overrides) proc = subprocess.Popen( [PYTHON, "-m", "ghostvault"], stdin=subprocess.PIPE, stdout=su
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 examples/scripts/mcp_security_test.py
low Shell/command execution in packaging/dev tooling (tests/test_browser_integration.py)MTC-SRC-002
In a packaging/dev/install script (shipped, but not the server runtime) (`tests/test_browser_integration.py:35`): 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: t subprocess out = subprocess.run( ["python", "-m", "camoufox", "path"], capture_output=True,
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 tests/test_browser_integration.py
Tools 5
Each tool and what it can reach — statically extracted from the published source.
gv_close_accountno sensitive capabilitygv_make_privateno sensitive capabilitygv_make_publicno sensitive capabilitygv_switch_accountno sensitive capabilitygv_unlockno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (5 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 |
|---|---|---|---|---|
v0.1.1b0 latest |
A 93/100 | 6 | 1.13.0 | 2026-08-25 |
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 ghostvault --online --registry pypiMore 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