AI agents call check_translation_integrity 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 performs a comparative analysis of translation files to check their integrity. It reads and compares data across multiple locale files but does not create, modify, delete, or execute external operations. The action is purely informational—determining consistency between locales. This is a typical Read operation with minimal risk.
From the tool's definition The tool 'check_translation_integrity' 'Compare[s] all locale files against the primary locale' — a comparison/verification operation with no modification or deletion of data.
Attacks that exploit this kind of access
Compare all locale files against the primary locale. 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_integrity: 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_integrity 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_integrity 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_integrity. 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_integrity 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 →