mac_draw_rectangle
AI agents invoke mac_draw_rectangle to trigger actions in Math MCP Server for MacOS. 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.
The tool likely triggers an external operation in Keynote (a macOS application) to draw a rectangle on a slide. This constitutes executing an action in an external application rather than a pure read or write of data. Confidence is reduced because the description is empty, requiring inference from the server context and tool name alone.
From the tool's definition Tool name 'mac_draw_rectangle' on a server that 'enables drawing shapes and adding text to slides' in Keynote (macOS application).
Attacks that exploit this kind of access
mac_draw_rectangle. It is categorised as a Execute tool in the Math MCP Server for MacOS MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Math MCP Server for MacOS MCP server in PolicyLayer and add a rule for mac_draw_rectangle: 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 Math MCP Server for MacOS. Nothing to install.
mac_draw_rectangle 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 mac_draw_rectangle 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 mac_draw_rectangle. 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.
mac_draw_rectangle is provided by the Math MCP Server for MacOS MCP server (rohinigaonkar/mcp-math-macos). 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 →