AI agents invoke browser_new_tab to trigger actions in Search. 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.
Opening a new tab is a browser action that initiates an external operation whose effects depend on subsequent arguments and user interaction. This falls under Execute rather than Read (which would be passive data retrieval like browser_get_text or browser_get_markdown). It does not Write data, is not Destructive, and is not Financial.
From the tool's definition Tool opens a new browser tab, triggering external browser operations. Grouped with other browser control tools (browser_click, browser_evaluate, browser_form_input_fill, browser_get_markdown) that manipulate a live browser environment.
Documented attack patterns abuse exactly the kind of access browser_new_tab gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_new_tab:
{
"version": "1",
"default": "deny",
"tools": {
"browser_new_tab": {
"limits": [
{
"counter": "browser_new_tab_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_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 tab. It is categorised as a Execute tool in the Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Search MCP server in PolicyLayer and add a rule for browser_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 Search. Nothing to install.
browser_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 browser_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 browser_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.
browser_new_tab is provided by the Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search, 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.
36 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.