Before writing to a project for the first time in a session, call assess_integration_state to understand client URL patterns and integration state. Import multiple translation keys into the sandbox at once. Accepts either inline JSON (translations parameter) or a path to a JSON file on disk (file...
AI agents use bulk_import 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 |
|---|---|---|---|
dryRun | boolean | — | If true, validate and preview what would be imported without writing anything |
contexts | object | — | Optional key -> context map (max 1000 chars per value). Context improves translation quality and reduces ambiguity. Good context describes: where the text appea |
filePath | string | — | Absolute path to a JSON file on disk. Format: { "locale": { "key": "value" } }. Use this for large translation files instead of inline JSON. |
namespace | string | Yes | Namespace slug — must already exist (use create_namespace first) |
projectSlug | string | Yes | Project slug |
translations | object | — | Inline locale → key → value map. Use this for small payloads. Example: { "en": { "save": "Save" }, "nb-NO": { "save": "Lagre" } } |
useBatchEndpoint | boolean | — | If true (default), use the bulk endpoint for faster imports. Falls back to individual requests if bulk returns 404. |
Parameters from the server's own tool schema.
This tool creates or modifies translation data (Write category) rather than merely reading it. While writes are sandboxed and reversible (not yet affecting production), the capability to import large volumes of translation keys represents a moderate risk if misused by an AI agent—it could corrupt localization data, overwrite existing translations, or introduce incorrect locale mappings.
From the tool's definition Tool description explicitly states 'Import multiple translation keys into the sandbox' and 'All writes go to sandbox', indicating it creates or modifies translation data in a reversible manner.
Risk signalsAccepts file system path (filePath) · Bulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Before writing to a project for the first time in a session, call assess_integration_state to understand client URL patterns and integration state. Import multiple translation keys into the sandbox at once. Accepts either inline JSON (translations parameter) or a path to a JSON file on disk (filePath parameter). File format: { "locale": { "key": "value" } } — same as inline translations. Use filePath when the payload is large (>100 keys) to avoid inline JSON size limits. All writes go to sandbox — production is unchanged until you promote. Run compare_local_vs_server first to avoid re-importing keys that already exist. 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_import accepts 7 parameters: dryRun, contexts, filePath, namespace, projectSlug, translations, useBatchEndpoint. Required: 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_import: 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_import 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_import 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_import. 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_import 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 →