AI agents call get_cursor_position to retrieve information from Iterm2 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves positional information from the terminal screen with no side effects. It does not execute commands, modify data, delete content, or move money. It is a read-only query that simply reports the current cursor location, making it a Read category risk with low severity.
From the tool's definition Tool returns cursor coordinates (x, y) without modifying any state or executing commands. The description indicates a pure query operation: 'Return the cursor coordinates.'
Attacks that exploit this kind of access
Return the cursor coordinates x, y within the visible screen. It is categorised as a Read tool in the Iterm2 MCP Server, which means it retrieves data without modifying state.
Register the Iterm2 MCP server in PolicyLayer and add a rule for get_cursor_position: 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 Iterm2. Nothing to install.
get_cursor_position 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_cursor_position 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_cursor_position. 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_cursor_position is provided by the Iterm2 MCP server (lorencarvalho/iterm2-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 →