Fetches the task screenshot. By default, a screenshot is automatically generated when a task is created, displaying the page in the browser exactly as the user saw it at that moment. A distinctive lilac marker on the screenshot indicates the location of the element on the page that the task refer...
AI agents call get_task_screenshot to retrieve information from Webvizio MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_task_screenshot only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Fetches the task screenshot. By default, a screenshot is automatically generated when a task is created, displaying the page in the browser exactly as the user saw it at that moment. A distinctive lilac marker on the screenshot indicates the location of the element on the page that the task refers to. In some cases, the task author may also add additional hints and instructions directly onto the screenshot. Use this tool if the task prompt lacks sufficient information for execution. Analyzing a screenshot can also be particularly useful for tasks related to layout or resolving visual bugs. Do not use this tool if the task and its solution methods are entirely clear from the task prompt. It is categorised as a Read tool in the Webvizio MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Webvizio MCP Server MCP server in PolicyLayer and add a rule for get_task_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 Webvizio MCP Server. Nothing to install.
get_task_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 get_task_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 get_task_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.
get_task_screenshot is provided by the Webvizio MCP Server MCP server (webvizio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.