AI agents invoke close_browser to trigger actions in OODA Computer Control. 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.
Closing a browser instance is an external operation that terminates a running process and performs cleanup. While it doesn't delete persistent data, it irreversibly ends the browser session and any unsaved state. It fits Execute as it triggers an external system operation, with medium severity since it could disrupt ongoing browser-based workflows managed by an AI agent.
From the tool's definition 'Close the browser instance and cleanup' — triggers an external operation (closing a running browser process and performing cleanup actions)
Documented attack patterns abuse exactly the kind of access close_browser gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OODA Computer Control, and nothing reaches the server without passing your rules. This is the rule we recommend for close_browser:
{
"version": "1",
"default": "deny",
"tools": {
"close_browser": {
"limits": [
{
"counter": "close_browser_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}close_browser 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.
Close the browser instance and cleanup. It is categorised as a Execute tool in the OODA Computer Control MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OODA Computer Control MCP server in PolicyLayer and add a rule for close_browser: 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 OODA Computer Control. Nothing to install.
close_browser 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 close_browser 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 close_browser. 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.
close_browser is provided by the OODA Computer Control MCP server (mnehmos/mnehmos.ooda.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OODA Computer Control, 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.
99 OODA Computer Control tools catalogued and risk-classified — across an index of 43,000+ MCP servers.