cloak_get_text
AI agents call cloak_get_text 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 text from web pages without modifying data, placing it in the Read category. Severity is medium rather than low because it operates through an anti-detection stealth browser (CloakBrowser), which could enable unauthorized scraping, evading access controls, or impersonation. The empty description lowers confidence slightly, but the server description and tool name provide sufficient clarity.
From the tool's definition Tool name 'cloak_get_text' indicates retrieval of text content from web pages. Server description states it 'Enables getting text, HTML, screenshots' which confirms read-only data retrieval.
Attacks that exploit this kind of access
cloak_get_text. 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_text: 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_text 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_text 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_text. 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_text 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 →