Resize a window. w/h can be pixels or 0.0-1.0 percentage.
AI agents invoke cond_resize_window 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 operation (resizing a window) in the terminal/UI environment. It doesn't read data, write persistent data, or destroy data irreversibly, but it does interact with and modify the state of an external window/process. Given the broader server context of direct terminal access and REPL session management, misuse could disrupt running sessions, though blast radius is moderate.
From the tool's definition Resize a window. w/h can be pixels or 0.0-1.0 percentage.
Attacks that exploit this kind of access
Resize a window. w/h can be pixels or 0.0-1.0 percentage. 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_resize_window: 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_resize_window 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_resize_window 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_resize_window. 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_resize_window 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 →