開啟 url 並回傳渲染後的 HTML 原始碼（適合做結構化解析 / 抽取連結）。
AI agents call cloak_get_html to retrieve information from Cloakbrowser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and returns HTML content from a URL. While it uses a stealth browser (CloakBrowser) to bypass detection measures, the action itself is purely passive data retrieval. It does not create, modify, delete, execute code, or move money. The anti-detection features are a means of retrieval, not a change in the fundamental operation category.
From the tool's definition Tool name 'cloak_get_html' and description indicate it 'opens url and returns rendered HTML source code (suitable for structured parsing / extracting links)' — a retrieval operation with no modification or execution of commands.
Attacks that exploit this kind of access
開啟 url 並回傳渲染後的 HTML 原始碼（適合做結構化解析 / 抽取連結）。. It is categorised as a Read tool in the Cloakbrowser MCP Server, which means it retrieves data without modifying state.
Register the Cloakbrowser MCP server in PolicyLayer and add a rule for cloak_get_html: 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 Cloakbrowser. Nothing to install.
cloak_get_html 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 cloak_get_html 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 cloak_get_html. 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.
cloak_get_html is provided by the Cloakbrowser MCP server (oliver0804/cloakbrowser-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 →