AI agents call check_translation_quality to retrieve information from I18n without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes translation quality metrics without creating, modifying, deleting, or executing any operations. It is a diagnostic read-only function that inspects existing translation data. The severity is low because misuse would only expose or analyze translation metadata without enabling data loss, financial impact, or code execution.
From the tool's definition Tool name 'check_translation_quality' and description indicate it 'returns issues per locale per key' — a query/inspection operation with no modification or side effects.
Attacks that exploit this kind of access
Check translation quality for specific keys. Returns issues per locale per key:. It is categorised as a Read tool in the I18n MCP Server, which means it retrieves data without modifying state.
Register the I18n MCP server in PolicyLayer and add a rule for check_translation_quality: 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 I18n. Nothing to install.
check_translation_quality 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 check_translation_quality 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 check_translation_quality. 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.
check_translation_quality is provided by the I18n MCP server (robin-heat/i18n-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 →