Get the page title 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.
AI agents call browser_get-title 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.
This tool retrieves page metadata (title) via browser automation. While it involves browser automation, the described use cases (JS-heavy SPA scraping, login flows, content retrieval) are fundamentally read operations that extract data without modifying systems or executing arbitrary code. The mention of 'AIDefence PII gating before content reaches Claude' further indicates this is a defensive read operation.
From the tool's definition Tool description states it 'Get[s] the page title' and is used for 'scraping' and 'content' retrieval. The phrase 'native WebFetch is faster and free' for static pages confirms this is a data retrieval operation without modification or execution of arbitrary…
Attacks that exploit this kind of access
Get the page title 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_get-title: 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_get-title 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_get-title 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_get-title. 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_get-title 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.