Alternative translation method: translate English text to project locales using backend AI (Gemini). Prefer agent-local translation (translate yourself, then set_translation + check_entry_quality) for better quality. Use this tool for bulk-filling new locales (100+ keys) or when the user explicit...
AI agents call ai_translate to retrieve information from Localization without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | English text to translate |
context | string | — | Context about where/how this key is used (max 1000 chars). Helps AI translate ambiguous strings accurately. Describe: screen, UI element type, meaning in this p |
projectSlug | string | Yes | Project slug for usage tracking |
targetLocales | array | — | Optional list of locale codes to translate into (e.g. ["uk", "nb-NO"]). When omitted, translates to all non-default project locales. Use this for efficiency whe |
Parameters from the server's own tool schema.
Even though ai_translate only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Alternative translation method: translate English text to project locales using backend AI (Gemini). Prefer agent-local translation (translate yourself, then set_translation + check_entry_quality) for better quality. Use this tool for bulk-filling new locales (100+ keys) or when the user explicitly requests backend translation. Returns translations for each configured locale. Usage is tracked per project. Optionally accepts context (where the text appears in UI) to improve translation quality for short or ambiguous strings. Optionally accepts targetLocales array to restrict translation to specific locales instead of all project locales. It is categorised as a Read tool in the Localization MCP Server, which means it retrieves data without modifying state.
ai_translate accepts 4 parameters: text, context, projectSlug, targetLocales. Required: text, projectSlug. The full parameter table on this page comes from the server's own tool schema.
Register the Localization MCP server in PolicyLayer and add a rule for ai_translate: 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 Localization. Nothing to install.
ai_translate 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 ai_translate 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 ai_translate. 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.
ai_translate is provided by the Localization MCP server (localization-mcp-server). 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 →