Fill a form field with human-like typing (anti-detection). Uses real keyboard events via CDP Input domain.
AI agents invoke browser_fill_form 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 triggers real keyboard input events in a browser via Chrome DevTools Protocol, constituting execution of UI actions with external effects. The 'anti-detection' framing and use of CDP Input domain confirm it actively drives browser interaction rather than just reading data. Misuse could submit forms, enter credentials, or manipulate web content, making it an Execute-category tool with medium severity.
From the tool's definition Fill a form field with human-like typing (anti-detection). Uses real keyboard events via CDP Input domain.
Documented attack patterns abuse exactly the kind of access browser_fill_form 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_fill_form:
{
"version": "1",
"default": "deny",
"tools": {
"browser_fill_form": {
"limits": [
{
"counter": "browser_fill_form_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_fill_form 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.
Fill a form field with human-like typing (anti-detection). Uses real keyboard events via CDP Input domain. 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_fill_form: 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_fill_form 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_fill_form 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_fill_form. 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_fill_form 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.