Nodriver Proxy MCP Server
nodriver-proxy-mcp
PyPI
v1.0.1
Published by bobongku — 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 5
high Shell/command execution in server code (src/nodriver_proxy_mcp/browser/session_manager.py)MTC-SRC-002
In the server's implementation (`src/nodriver_proxy_mcp/browser/session_manager.py:243`): 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: True proc = subprocess.Popen(cmd, **popen_kwargs) if not self._wait_for_ipc(ipc_port, timeout=10.
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/nodriver_proxy_mcp/browser/session_manager.py
high Shell/command execution in server code (src/nodriver_proxy_mcp/codemode/tools.py)MTC-SRC-002
In the server's implementation (`src/nodriver_proxy_mcp/codemode/tools.py:113`): 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: subprocess.run( ["taskkill", "/F", "/T", "/PID", str(pid)], ca
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/nodriver_proxy_mcp/codemode/tools.py
high Shell/command execution in server code (src/nodriver_proxy_mcp/proxy/controller.py)MTC-SRC-002
In the server's implementation (`src/nodriver_proxy_mcp/proxy/controller.py:91`): 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: self._proc = subprocess.Popen(cmd, **popen_kwargs) self._port = port # Drain stderr in ba
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/nodriver_proxy_mcp/proxy/controller.py
high Shell/command execution in server code (src/nodriver_proxy_mcp/sdk.py)MTC-SRC-002
In the server's implementation (`src/nodriver_proxy_mcp/sdk.py:682`): 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: True proc = subprocess.Popen(cmd, **popen_kwargs) if not _wait_for_port(ipc_port, timeout=15.0):
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/nodriver_proxy_mcp/sdk.py
medium Untrusted input can drive an external actionMTC-FLOW-005
Untrusted-input tools ([browser_intercept_disable, browser_list_intercept_rules, list_interception_rules]) co-exist with external-action tools ([generate_curl]). A prompt injection could cause unwanted external actions, though no direct sensitive-data leak path was found.
Evidence: untrusted [browser_intercept_disable, browser_list_intercept_rules, list_interception_rules] → sinks [generate_curl]
Fix: Require confirmation for state-changing/egress actions triggered after processing untrusted content.
Location: flow browser_intercept_disable → generate_curl
Tools 39
Each tool and what it can reach — statically extracted from the published source.
browser_intercept_disableingests untrusted inputbrowser_list_intercept_rulesingests untrusted inputgenerate_curlnetwork egresslist_interception_rulesingests untrusted inputadd_interception_ruleno sensitive capabilitybrowser_backno sensitive capabilitybrowser_clickno sensitive capabilitybrowser_closeno sensitive capabilitybrowser_get_consoleno sensitive capabilitybrowser_get_domno sensitive capability
Show 29 more tools ↓
browser_get_storageno sensitive capabilitybrowser_get_textno sensitive capabilitybrowser_gono sensitive capabilitybrowser_intercept_requestno sensitive capabilitybrowser_intercept_responseno sensitive capabilitybrowser_jsno sensitive capabilitybrowser_list_sessionsno sensitive capabilitybrowser_list_tabsno sensitive capabilitybrowser_openno sensitive capabilitybrowser_screenshotno sensitive capabilitybrowser_set_cookieno sensitive capabilitybrowser_typeno sensitive capabilitybrowser_waitno sensitive capabilityclear_trafficno sensitive capabilitydetect_auth_patternno sensitive capabilityexecute_security_codeno sensitive capabilityextract_from_flowno sensitive capabilityextract_session_variableno sensitive capabilityfuzz_endpointno sensitive capabilityget_traffic_summaryno sensitive capabilityinspect_flowno sensitive capabilitylist_session_variablesno sensitive capabilitymanage_proxyno sensitive capabilityproxy_statusno sensitive capabilityremove_interception_ruleno sensitive capabilityreplay_flowno sensitive capabilitysearch_trafficno sensitive capabilitysend_raw_requestno sensitive capabilityset_scopeno 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 (39 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 |
|---|---|---|---|---|
v1.0.1 latest |
A 93/100 | 5 | 1.8.0 | 2026-07-23 |
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 nodriver-proxy-mcp --online --registry pypiMore in Developer Tools
Security scan results for the 1stay MCP server.
Security scan results for the Adguard Home MCP server.
Security scan results for the Ado Browser MCP server.
Security scan results for the Adobe Experience Dev MCP server.
Security scan results for the Aemet MCP server.
Security scan results for the Affinity Mcp Bridge MCP server.