Get AI-optimized accessibility tree snapshot with element refs (@e1, @e2, etc.) 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 Claud...
AI agents call browser_snapshot 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 primarily reads/captures browser state (accessibility tree, DOM snapshot). However, it involves real browser automation with cookie reuse and login flow support, which could expose sensitive session data or bypass PII controls. No explicit write or destructive action is described, but the browser automation context and login/cookie handling elevate severity to medium.
From the tool's definition 'Get AI-optimized accessibility tree snapshot' — retrieves a snapshot of the browser DOM/accessibility tree; 'JS-heavy SPA scraping, login flows with cookie reuse' — reads page content via real browser automation
Attacks that exploit this kind of access
Get AI-optimized accessibility tree snapshot with element refs (@e1, @e2, etc.) 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_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 Claude Flow. Nothing to install.
browser_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 browser_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 browser_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.
browser_snapshot 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.