Get a comprehensive snapshot of the current Safari page in one call: URL, title, h1, meta description, visible text preview, link count, primary nav links (from <nav> element — text + path), form field count + labels (for fill_form), image count, table count, scroll position, viewport size, page ...
AI agents call page_snapshot 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.
page_snapshot performs passive information gathering about the current state of a webpage. It reads and aggregates existing page data (DOM elements, text content, metadata, scroll position, viewport dimensions) without modifying anything. This is a pure Read operation with minimal risk—the worst case is an AI agent obtaining unwanted visibility into page structure, which carries low severity.
From the tool's definition Tool description states it 'Get[s] a comprehensive snapshot of the current Safari page' including 'URL, title, h1, meta description, visible text preview, link count, primary nav links, form field count + labels, image count, table count, scroll position,…
Attacks that exploit this kind of access
Get a comprehensive snapshot of the current Safari page in one call: URL, title, h1, meta description, visible text preview, link count, primary nav links (from <nav> element — text + path), form field count + labels (for fill_form), image count, table count, scroll position, viewport size, page heading outline (h1-h3 with IDs for scroll_to_element), and visible buttons. Use at the start of automation to understand what page is loaded, its structure, and what actions are available. Buttons with identical text are merged with a count field (e.g. {text:. 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 page_snapshot: 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.
page_snapshot 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 page_snapshot 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 page_snapshot. 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.
page_snapshot 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 →