translate_text · i18n Agent MCP: Risk & Policy

WHAT IT DOES

What translate_text does on i18n Agent

AI agents use translate_text to create or update resources in i18n Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your i18n Agent environment.

WHY IT NEEDS A POLICY

Why translate_text needs a policy

This tool takes text and produces a translated version. It writes/creates new content (the translation) but does not delete anything, execute code, move money, or cause irreversible side effects. The blast radius of misuse is low — at worst, incorrect translations are produced, which can be corrected.

From the tool's definition "Translate text from one language to another with cultural context" — the tool transforms input text and produces a translated output.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

translate_text Rate-limited

translate_text stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "translate_text": {
      "limits": [
        {
          "counter": "translate_text_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches i18n Agent, so you can run agents against it safely.

FAQ

Questions about translate_text

What does the translate_text tool do? +

Translate text from one language to another with cultural context. It is categorised as a Write tool in the i18n Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on translate_text? +

Register the i18n Agent MCP server in PolicyLayer and add a rule for translate_text: 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 Agent. Nothing to install.

What risk level is translate_text? +

translate_text is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit translate_text? +

Yes. Add a rate_limit block to the translate_text 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.

How do I block translate_text completely? +

Set action: deny in the PolicyLayer policy for translate_text. 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.

What MCP server provides translate_text? +

translate_text is provided by the i18n Agent MCP server (loking/mcp-client). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

translate_text is one line of i18n Agent's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →