Inject anti-detection patches into Chrome/Electron page. Call once after navigating to a protected site. Hides webdriver flag, patches plugins/languages/permissions.
AI agents invoke browser_stealth to trigger actions in ScreenHand. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes JavaScript injections into a browser page to modify runtime properties and evade detection mechanisms. It triggers external operations (patching browser fingerprint, hiding automation flags) whose effects depend on the target page. It does not delete data or move money, but it actively manipulates the browser environment to circumvent security controls, placing it firmly in Execute.
From the tool's definition Inject anti-detection patches into Chrome/Electron page. Hides webdriver flag, patches plugins/languages/permissions.
Documented attack patterns abuse exactly the kind of access browser_stealth gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScreenHand, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_stealth:
{
"version": "1",
"default": "deny",
"tools": {
"browser_stealth": {
"limits": [
{
"counter": "browser_stealth_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_stealth stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Inject anti-detection patches into Chrome/Electron page. Call once after navigating to a protected site. Hides webdriver flag, patches plugins/languages/permissions. It is categorised as a Execute tool in the ScreenHand MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ScreenHand MCP server in PolicyLayer and add a rule for browser_stealth: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ScreenHand. Nothing to install.
browser_stealth is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser_stealth rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_stealth. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_stealth is provided by the ScreenHand MCP server (manushi4/screenhand). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScreenHand, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
89 ScreenHand tools catalogued and risk-classified — across an index of 43,000+ MCP servers.