browser_fill_form
AI agents invoke browser_fill_form to trigger actions in Camoufox. 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.
Form filling in a browser automation context involves interacting with web forms, which can trigger submissions, logins, signups, or other external operations. The anti-detection framing suggests use in automated contexts where forms may be filled to mimic human behavior. This is an Execute-level action as it drives browser interactions with external side effects.
From the tool's definition Tool name: browser_fill_form; server description mentions 'form filling' as a core capability of this browser automation server with anti-detection features.
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 Camoufox, 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.
browser_fill_form. It is categorised as a Execute tool in the Camoufox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Camoufox 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 Camoufox. 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 Camoufox MCP server (rlgrpe/camoufox-mcp-python). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Camoufox, 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.
22 Camoufox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.