Gets the title of the currently active window.
AI agents call get_active_window_title to retrieve information from Ubuntu VM Control without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about the current GUI state (active window title) with no side effects. It is a pure read operation analogous to querying system state. While it operates within a VM control system, the specific tool itself only reads data and does not execute commands, modify files, or trigger actions.
From the tool's definition Tool name 'get_active_window_title' and description 'Gets the title of the currently active window' indicate a query operation that retrieves window metadata without modifying state or executing external operations.
Attacks that exploit this kind of access
Gets the title of the currently active window. It is categorised as a Read tool in the Ubuntu VM Control MCP Server, which means it retrieves data without modifying state.
Register the Ubuntu VM Control MCP server in PolicyLayer and add a rule for get_active_window_title: 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 Ubuntu VM Control. Nothing to install.
get_active_window_title 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 get_active_window_title 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 get_active_window_title. 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.
get_active_window_title is provided by the Ubuntu VM Control MCP server (ltcg-addict/ubuntu). 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 →