AI agents call browser_get_content 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 HTML content from a web page, which is a read-only operation with no side effects. While the browser is controlled remotely, the action itself (fetching HTML) does not execute code, modify data, delete resources, or move money. The severity is low because HTML content retrieval poses minimal risk even if misused by an agent—it cannot alter state or cause irreversible harm.
From the tool's definition Tool name 'browser_get_content' and description 'Get HTML content of the page or an element' indicate retrieval of page data with no modification or execution of external operations.
Attacks that exploit this kind of access
Get HTML 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_content: 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_content 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_content 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_content. 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_content 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 →