AI agents use i18n_create_key to create or update resources in Shipeasy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Shipeasy environment.
This tool creates new internationalization keys in a profile. While the operation is reversible (keys can be deleted), it modifies application configuration/translation data. The insert-only semantics prevent accidental overwrites, reducing risk.
From the tool's definition 'Add a single new key to a profile' describes creating new data. 'Insert-only: if the key already exists it is left unchanged (never overwritten)' confirms this is a creation operation with no overwrite capability, making it reversible write rather than…
Attacks that exploit this kind of access
Add a single new key to a profile. Insert-only: if the key already exists it is left unchanged (never overwritten). It is categorised as a Write tool in the Shipeasy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Shipeasy MCP server in PolicyLayer and add a rule for i18n_create_key: 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 Shipeasy. Nothing to install.
i18n_create_key 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 i18n_create_key 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 i18n_create_key. 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.
i18n_create_key is provided by the Shipeasy MCP server (shipeasy-ai/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 →