AI agents call browser_scan_i18n_leaks to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and inspects page content for internationalization issues. It has no side effects, does not modify data, execute external operations, or affect system state. It is a diagnostic/scanning utility that qualifies as a Read operation with low severity since misuse would only expose information about missing translations, posing minimal risk.
From the tool's definition Tool performs 'scan' of 'visible page text and document.title' to detect untranslated i18n keys. The action retrieves and analyzes data without modification, deletion, or execution of code/commands.
Attacks that exploit this kind of access
Scan visible page text and document.title for untranslated i18n keys (e.g. page_profile.public_profile.fallback.birthday). It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for browser_scan_i18n_leaks: 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 Mcp. Nothing to install.
browser_scan_i18n_leaks 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_scan_i18n_leaks 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_scan_i18n_leaks. 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_scan_i18n_leaks is provided by the MCP server (victormyschik/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 →