Focus a window by app-id or name (fuzzy match).
AI agents invoke cond_focus to trigger actions in TermPipe MCP. 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 UI operation — focusing a window — which is a side-effectful action that manipulates the desktop/windowing environment. It doesn't just read data; it actively changes which window has focus, which can affect user interaction and enable further automated actions. It falls under Execute as it triggers an external operation on the system's window manager.
From the tool's definition Focus a window by app-id or name (fuzzy match)
Attacks that exploit this kind of access
Focus a window by app-id or name (fuzzy match). It is categorised as a Execute tool in the TermPipe MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TermPipe MCP server in PolicyLayer and add a rule for cond_focus: 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 TermPipe MCP. Nothing to install.
cond_focus 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 cond_focus 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 cond_focus. 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.
cond_focus is provided by the TermPipe MCP server (wbind-core/termpipe-mcp). 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 →