AI agents call find_window_list to retrieve information from MaaMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The function appears to enumerate or query available windows on a Windows desktop system, which is a passive information-gathering operation. There are no indications of state modification, command execution with variable outcomes, deletion, or financial impact. Empty description lowers confidence slightly, but the naming convention strongly suggests Read category.
From the tool's definition Tool name 'find_window_list' indicates a query/discovery operation that lists windows. The description is empty, but the name clearly suggests retrieval of window information without modification.
Attacks that exploit this kind of access
find_window_list. It is categorised as a Read tool in the MaaMCP MCP Server, which means it retrieves data without modifying state.
Register the Maa MCP server in PolicyLayer and add a rule for find_window_list: 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 MaaMCP. Nothing to install.
find_window_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the find_window_list 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 find_window_list. 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.
find_window_list is provided by the Maa MCP server (maa-ai/maamcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →