AI agents call i18n_codemod_preview to retrieve information from Shipeasy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays a preview of potential code transformations (AST diffs) without actually modifying any data or files. It is a read-only operation that allows inspection of what changes would occur, making it purely informational with no side effects. The low severity reflects minimal risk even if misused—an AI agent cannot cause harm by previewing diffs.
From the tool's definition Tool description explicitly states 'Returns a diff; writes nothing.' The function is a preview/analysis operation that performs an AST transform analysis without persisting any changes.
Attacks that exploit this kind of access
Preview an AST transform that wraps translatable strings in <ShipeasyString> or shipeasy_t(). Returns a diff; writes nothing. It is categorised as a Read tool in the Shipeasy MCP Server, which means it retrieves data without modifying state.
Register the Shipeasy MCP server in PolicyLayer and add a rule for i18n_codemod_preview: 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_codemod_preview is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the i18n_codemod_preview 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_codemod_preview. 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_codemod_preview 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 →