AI agents use create_asset to create or update resources in Localise — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Localise environment.
This tool creates new translation keys within a translation management system, which is a reversible write operation. It does not read data (Read), execute arbitrary code (Execute), delete data (Destructive), or move funds (Financial). The impact is limited to adding configuration data to a translation service with minimal side effects; if created in error, keys can be deleted or modified.
From the tool's definition Tool name 'create_asset' combined with description 'Create a new translation key (asset) in localise.biz' indicates data creation via a translation management API.
Attacks that exploit this kind of access
Create a new translation key (asset) in localise.biz. It is categorised as a Write tool in the Localise MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Localise MCP server in PolicyLayer and add a rule for create_asset: 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 Localise. Nothing to install.
create_asset 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 create_asset 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 create_asset. 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.
create_asset is provided by the Localise MCP server (localise-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 →