AI agents call i18n_discover_site 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 fetches and parses URL content (specifically HTML link tags) to discover i18n resources. It is a read-only operation that retrieves data from a URL without creating, modifying, deleting, or executing code. The incomplete description ('parse <link rel=') suggests it extracts metadata from HTML, which is a pure read operation. No write, execute, destructive, or financial operations are indicated.
From the tool's definition Tool name 'i18n_discover_site' and description 'Fetch a URL, parse <link rel=' indicates retrieval and parsing of web content without modification or side effects.
Attacks that exploit this kind of access
Fetch a URL, parse <link rel=. 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_discover_site: 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_discover_site 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_discover_site 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_discover_site. 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_discover_site 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 →