Get the screen or viewport dimensions as [width, height].
AI agents call get_dimensions to retrieve information from ComputerMate without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns screen/viewport dimensions without modifying any state, executing code, or accessing sensitive data. It is a straightforward read operation with minimal security risk. Even if misused by an agent, it can only retrieve display metadata, which is already known to the agent (it controls the screen). Low severity due to negligible impact.
From the tool's definition Tool name 'get_dimensions' and description 'Get the screen or viewport dimensions' indicate a retrieval operation that returns display dimensions with no side effects.
Attacks that exploit this kind of access
Get the screen or viewport dimensions as [width, height]. It is categorised as a Read tool in the ComputerMate MCP Server, which means it retrieves data without modifying state.
Register the ComputerMate MCP server in PolicyLayer and add a rule for get_dimensions: 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 ComputerMate. Nothing to install.
get_dimensions 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_dimensions 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_dimensions. 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_dimensions is provided by the ComputerMate MCP server (one710/computermate). 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 →