AI agents invoke browser_type to trigger actions in Playwright. 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.
Playwright's browser_type action types text into a browser element, which is an interactive browser operation. While the description is empty, the Playwright context and sibling tools strongly suggest this triggers external browser interactions. Typing into forms can submit data, enter credentials, or trigger workflows — making it an Execute-level action. Confidence is moderate due to the empty description.
From the tool's definition Tool name 'browser_type' on a Playwright server alongside sibling tools like browser_click, browser_drag, browser_close — all browser automation actions. 'browser_type' likely simulates keyboard input into browser elements.
Documented attack patterns abuse exactly the kind of access browser_type gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_type:
{
"version": "1",
"default": "deny",
"tools": {
"browser_type": {
"limits": [
{
"counter": "browser_type_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browser_type 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_type. It is categorised as a Execute tool in the Playwright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright MCP server in PolicyLayer and add a rule for browser_type: 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 Playwright. Nothing to install.
browser_type 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_type 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_type. 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_type is provided by the Playwright MCP server (@playwright/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright, 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.
68 Playwright tools catalogued and risk-classified — across an index of 43,000+ MCP servers.