Capture screenshot of the page Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. For static HTML pages, native WebFetch is fast...
AI agents call browser_screenshot to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool captures (reads) a visual snapshot of a browser page. It does not write, delete, or execute arbitrary code directly. However, it involves real browser automation including login flows with cookie reuse, which means it can access authenticated sessions and capture potentially sensitive content (PII gating is mentioned).
From the tool's definition Capture screenshot of the page — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions
Attacks that exploit this kind of access
Capture screenshot of the page Use when native WebFetch is wrong because you need real browser automation — JS-heavy SPA scraping, login flows with cookie reuse, replay against DOM-drifted versions, AIDefence PII gating before content reaches Claude. For static HTML pages, native WebFetch is faster and free. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for browser_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 Claude Flow. Nothing to install.
browser_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 browser_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 browser_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.
browser_screenshot is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.