AI agents invoke new_tab to trigger actions in Webclaw. 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 a real Chrome browser action, so it qualifies as Execute rather than Read. However, opening a tab is a low-risk operation with minimal blast radius: it cannot delete data, modify sensitive state, move money, or compromise security if invoked unexpectedly. An AI agent opening tabs poses low practical harm (resource waste, minor annoyance), making severity 'low' appropriate.
From the tool's definition Opens a new browser tab—a direct browser action that performs an external operation with side effects. The description is minimal but clear: 'Open a new browser tab.'
Documented attack patterns abuse exactly the kind of access new_tab gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Webclaw, and nothing reaches the server without passing your rules. This is the rule we recommend for new_tab:
{
"version": "1",
"default": "deny",
"tools": {
"new_tab": {
"limits": [
{
"counter": "new_tab_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}new_tab 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.
Open a new browser tab. It is categorised as a Execute tool in the Webclaw MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Webclaw MCP server in PolicyLayer and add a rule for new_tab: 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 Webclaw. Nothing to install.
new_tab 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 new_tab 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 new_tab. 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.
new_tab is provided by the Webclaw MCP server (kuroko1t/webclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Webclaw, 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.
21 Webclaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.