capture_page_screenshot
Capture a screenshot of the current page/tab via CDP and optionally save it to a file path.
This record as markdown: /tools/335234131-agent-browser-mcp/capture-page-screenshot.md
What capture_page_screenshot does on Agent Browser
AI agents call capture_page_screenshot to retrieve information from Agent Browser without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why capture_page_screenshot is rated Low
Screenshot capture is a read operation—it queries and retrieves the visual representation of the current page state without side effects or modifications. However, severity is medium rather than low because: (1) screenshots can leak sensitive information visible on screen (credentials, personal data, API keys in dev tools), (2) the tool has access to full browser context including login sessions and cookies as noted…
From the tool's definition Tool name 'capture_page_screenshot' and description state it 'Capture[s] a screenshot of the current page/tab' with optional file save. This retrieves visual data from the browser without modifying page state or executing arbitrary code.
Attacks that exploit this kind of access
The rule that runs capture_page_screenshot safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agent Browser, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For capture_page_screenshot, this is the rule to start with:
capture_page_screenshot is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Agent Browser, apply this rule, and every capture_page_screenshot call is checked against it from then on.
Questions about capture_page_screenshot
Capture a screenshot of the current page/tab via CDP and optionally save it to a file path. It is categorised as a Read tool in the Agent Browser MCP Server, which means it retrieves data without modifying state.
Register the Agent Browser MCP server in PolicyLayer and add a rule for capture_page_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 Agent Browser. Nothing to install.
capture_page_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 capture_page_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 capture_page_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.
capture_page_screenshot is provided by the Agent Browser MCP server (335234131/agent-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agent Browser, and thousands of servers like it.
This server
Across the catalogue