Closes the browser window. Login sessions are saved and will be reused next time.
AI agents invoke close_browser to trigger actions in Auth Fetch. 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 an external browser operation (closing a browser window) and persists session state to disk. While it terminates a process, it also has a side effect of saving login sessions locally for future reuse, making it more than a simple read. It fits Execute as it controls an external browser process and modifies stored session profiles.
From the tool's definition Closes the browser window. Login sessions are saved and will be reused next time.
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 Auth Fetch, 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.
Closes the browser window. Login sessions are saved and will be reused next time. It is categorised as a Execute tool in the Auth Fetch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Auth Fetch 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 Auth Fetch. 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 Auth Fetch MCP server (ymw0407/auth-fetch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Auth Fetch tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Auth Fetch tools catalogued and risk-classified — across an index of 42,500+ MCP servers.