AI agents call browser_close as a supporting operation in Amazon Data Processing MCP Server workflows.
The tool name suggests closing a browser instance, which would be an Execute-type action (terminating a process). However, the description is completely empty, and the server context (Amazon data processing) makes the presence of a browser tool unusual. Without any description to confirm behavior, confidence is low.
From the tool's definition Tool name is 'browser_close' but description is empty and uninformative. The server context is 'Amazon Data Processing MCP Server'.
Documented attack patterns abuse exactly the kind of access browser_close gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Amazon Data Processing MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_close:
{
"version": "1",
"default": "deny",
"tools": {
"browser_close": {
"limits": [
{
"counter": "browser_close_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
} browser_close gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
browser_close. It is categorised as a Other tool in the Amazon Data Processing MCP Server MCP Server, which means it performs auxiliary operations.
Register the Amazon Data Processing MCP Server MCP server in PolicyLayer and add a rule for browser_close: 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 Amazon Data Processing MCP Server. Nothing to install.
browser_close is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_close 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_close. 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_close is provided by the Amazon Data Processing MCP Server MCP server (awslabs.aws-dataprocessing-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Amazon Data Processing MCP Server, 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.
805 Amazon Data Processing MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.