AI agents call browser_check_captcha 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.
The tool only reads and reports on the current page state — it detects CAPTCHAs and returns screenshots without modifying anything. However, the explicit note that 'The screenshot can be analyzed to solve image-based CAPTCHAs' signals the tool's intent to facilitate CAPTCHA circumvention, which is a security concern.
From the tool's definition Check if a CAPTCHA is present on the current page. Returns detection info and screenshots of any CAPTCHA found.
Attacks that exploit this kind of access
Check if a CAPTCHA is present on the current page. Returns detection info and screenshots of any CAPTCHA found. The screenshot can be analyzed to solve image-based CAPTCHAs. 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_check_captcha: 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_check_captcha 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_check_captcha 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_check_captcha. 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_check_captcha 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 →