AI agents call ai.translate to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Translation is a read-only operation that processes input text and returns transformed output without modifying any underlying data, executing arbitrary code, triggering external systems, deleting resources, or moving funds. The severity is low because even if misused by an agent, the worst outcome is incorrect or unexpected translations with no destructive or financial consequences.
From the tool's definition Tool performs translation of text from a source language to a target language. The description indicates it 'translates text' with no mention of data modification, deletion, code execution, or financial operations.
Attacks that exploit this kind of access
Translate text into a target language. Source language auto-detected if omitted. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for ai.translate: 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 Mcp. Nothing to install.
ai.translate 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 ai.translate 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 ai.translate. 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.
ai.translate is provided by the MCP server (@2sio/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 →