Run a low-level browser command. Use over Stagehand when you need precise, deterministic control — element-by-ref interactions, DOM inspection, network debugging, JS evaluation. Shares the same browser session as Stagehand.
Part of the Browser Automation server.
Free to start. No card required.
AI agents invoke agent_browser_run to trigger processes or run actions in Browser Automation. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
agent_browser_run can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"agent_browser_run": {
"limits": [
{
"counter": "agent_browser_run_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Browser Automation policy for all 13 tools.
These attack patterns abuse exactly the kind of access agent_browser_run gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Run a low-level browser command. Use over Stagehand when you need precise, deterministic control — element-by-ref interactions, DOM inspection, network debugging, JS evaluation. Shares the same browser session as Stagehand.. It is categorised as a Execute tool in the Browser Automation MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser Automation MCP server in PolicyLayer and add a rule for agent_browser_run: 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 Browser Automation. Nothing to install.
agent_browser_run 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 agent_browser_run 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 agent_browser_run. 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.
agent_browser_run is provided by the Browser Automation MCP server (@popoverai/browser-automation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 13 Browser Automation tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.