get_web_screenshots
AI agents call get_web_screenshots to retrieve information from Gemini Web Automation MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name implies fetching/reading screenshot images from web automation sessions, which is a read operation. However, the empty description lowers confidence. Given the server context of web browsing automation, screenshots are typically read-only captures of browser state. Severity is medium because screenshots could capture sensitive information displayed in the browser.
From the tool's definition Tool name 'get_web_screenshots' suggests retrieval of screenshot data; description is empty and uninformative.
Attacks that exploit this kind of access
get_web_screenshots. It is categorised as a Read tool in the Gemini Web Automation MCP MCP Server, which means it retrieves data without modifying state.
Register the Gemini Web Automation MCP server in PolicyLayer and add a rule for get_web_screenshots: 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 Gemini Web Automation MCP. Nothing to install.
get_web_screenshots 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_web_screenshots 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_web_screenshots. 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_web_screenshots is provided by the Gemini Web Automation MCP server (vincenthopf/computer-use-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 →