Translate text between languages using Kagi Translate.
AI agents call translate_text to retrieve information from Kagi Translate MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The translate_text tool reads input text and returns translated output without modifying, creating, deleting, or executing any operations on persistent data or external systems beyond the translation service call itself. It is a pure read operation that transforms data in-transit for informational purposes only.
From the tool's definition Tool translates text between languages using Kagi Translate API. The description indicates it 'translate[s] text' which is a retrieval/transformation operation with no side effects on underlying data.
Attacks that exploit this kind of access
Translate text between languages using Kagi Translate. It is categorised as a Read tool in the Kagi Translate MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kagi Translate MCP Server 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 Kagi Translate MCP Server. Nothing to install.
translate_text 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 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.
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.
translate_text is provided by the Kagi Translate MCP Server MCP server (subhangadirli/kagi-translate-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 →