AI agents use i18n_install_loader 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 or modifies code by emitting/installing a script loader for internationalization purposes. It performs a reversible Write action (adding a script tag/loader configuration) rather than reading data (Read), executing arbitrary operations (Execute), or destroying data (Destructive).
From the tool's definition Tool name 'i18n_install_loader' and description 'Emit the correct <script src=' indicate generation and insertion of script loader code into a project or configuration.
Attacks that exploit this kind of access
Emit the correct <script src=. 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_install_loader: 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_install_loader 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_install_loader 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_install_loader. 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_install_loader 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 →