ALWAYS call assess_integration_state at the start of a new session before writing. Alternative all-in-one: translate via backend AI (Gemini), save to sandbox, and quality-check in one step. Prefer agent-local translation for batches under 100 keys (translate yourself → set_translation → check_ent...
AI agents use bulk_translate_and_save to create or update resources in Localization — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Localization environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
entries | array | Yes | Array of entries to translate and save (1–200) |
namespace | string | Yes | Namespace slug |
projectSlug | string | Yes | Project slug |
skipQuality | boolean | — | Skip sync quality check; results queued for background worker (default: false) |
targetLocales | array | — | Optional list of locale codes. When omitted, translates to all non-default project locales. |
Parameters from the server's own tool schema.
This tool writes translations to the sandbox environment — creating or modifying translation data. While it uses backend AI for translation and includes quality checks, the core action is saving data. It targets sandbox (not production), which slightly limits blast radius, but bulk operations on 100+ keys could introduce widespread incorrect translations.
From the tool's definition translate via backend AI (Gemini), save to sandbox, and quality-check in one step... Saves translations directly to sandbox (not production)
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
ALWAYS call assess_integration_state at the start of a new session before writing. Alternative all-in-one: translate via backend AI (Gemini), save to sandbox, and quality-check in one step. Prefer agent-local translation for batches under 100 keys (translate yourself → set_translation → check_entry_quality). Use this for large bulk operations (100+ keys) or when the user explicitly requests backend translation. Saves translations directly to sandbox (not production). With skipQuality=false (default): returns per-key per-locale quality scores inline. With skipQuality=true: saves translations, queues quality check, returns immediately. Max 200 entries per call. It is categorised as a Write tool in the Localization MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
bulk_translate_and_save accepts 5 parameters: entries, namespace, projectSlug, skipQuality, targetLocales. Required: entries, namespace, 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 bulk_translate_and_save: 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.
bulk_translate_and_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the bulk_translate_and_save 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 bulk_translate_and_save. 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.
bulk_translate_and_save 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 →