AI agents call browser_get_text to retrieve information from MCProxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries rendered text from a web page without creating, modifying, deleting, or executing any operations. It is a passive read operation analogous to fetching/getting data. The low severity reflects minimal blast radius even if misused by an agent—it cannot alter state, execute code, delete data, or move funds. Confidence is high because the name and description are explicit and unambiguous.
From the tool's definition Tool name 'browser_get_text' and description 'Get visible text content of the page or an element' indicate pure data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get visible text content of the page or an element. It is categorised as a Read tool in the MCProxy MCP Server, which means it retrieves data without modifying state.
Register the MCProxy MCP server in PolicyLayer and add a rule for browser_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 MCProxy. Nothing to install.
browser_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 browser_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 browser_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.
browser_get_text is provided by the MCProxy MCP server (saladtechnologies/mcproxy). 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 →