AI agents call get_translations to retrieve information from I18n without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves translation data without side effects. It follows the Read category pattern of fetching/listing data (get_translation is a typical Read verb). The namespace and locale structure suggests it returns configuration or localization metadata. There is no capability to modify, delete, or execute operations, making this a straightforward Read classification with low severity.
From the tool's definition Tool retrieves translations in a read-only manner: 'Get all translations for a namespace' with no mention of modification, deletion, or execution. Returns structured data as key-value pairs.
Attacks that exploit this kind of access
Get all translations for a namespace as { key: { locale: value } } pairs. It is categorised as a Read tool in the I18n MCP Server, which means it retrieves data without modifying state.
Register the I18n MCP server in PolicyLayer and add a rule for get_translations: 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 I18n. Nothing to install.
get_translations 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 get_translations 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 get_translations. 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.
get_translations is provided by the I18n MCP server (robin-heat/i18n-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 →