Remove a translation key from all locale files in a namespace.
AI agents call delete_translation to permanently remove resources in I18n — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes translation keys from all locale files, which cannot be undone. While the blast radius is limited to i18n data (not production systems or financial data), the destructive nature of multi-file deletion and the inability to recover deleted keys makes this Destructive rather than Write.
From the tool's definition Tool description states 'Remove a translation key from all locale files in a namespace.' The verb 'Remove' combined with 'delete_translation' in the tool name indicates irreversible deletion of translation data across multiple locale files.
Attacks that exploit this kind of access
Remove a translation key from all locale files in a namespace. It is categorised as a Destructive tool in the I18n MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the I18n MCP server in PolicyLayer and add a rule for delete_translation: 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.
delete_translation is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the delete_translation 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 delete_translation. 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.
delete_translation 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 →