Capture a screenshot of the screen or a region. Returns a base64-encoded image. Defaults to JPEG at 1280px width for fast, compact results. Use region params (x, y, width, height) to capture just part of the screen - much faster and smaller for focused areas.
AI agents call screenshot to retrieve information from MacWright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are read-only operations that query the current visual state of the screen without creating, modifying, deleting, or executing any actions on the system. This is information retrieval only, making it a Read category tool with low severity since misuse would only expose visual information already visible on screen.
From the tool's definition Tool captures and returns a screenshot as a base64-encoded image with no modification of system state. Description explicitly states 'Capture a screenshot' and 'Returns a base64-encoded image' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Capture a screenshot of the screen or a region. Returns a base64-encoded image. Defaults to JPEG at 1280px width for fast, compact results. Use region params (x, y, width, height) to capture just part of the screen - much faster and smaller for focused areas. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.
Register the MacWright MCP server in PolicyLayer and add a rule for screenshot: 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 MacWright. Nothing to install.
screenshot 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 screenshot 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 screenshot. 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.
screenshot is provided by the MacWright MCP server (ruchit-p/macwright). 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 →