Proofread text with Kagi Translate.
AI agents call proofread 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.
Proofreading is fundamentally a Read operation—it retrieves and analyzes text to identify issues but does not create, modify, delete, or execute code. The output is analytical feedback, not data mutation or external action. The severity is low because even if misused by an AI agent, proofreading poses no risk to data integrity, financial systems, or system security.
From the tool's definition Tool description: 'Proofread text with Kagi Translate.' Proofreading is a read-only operation that analyzes text for grammar, spelling, and style issues without modifying the original data or triggering external side effects.
Attacks that exploit this kind of access
Proofread text with 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 proofread: 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.
proofread 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 proofread 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 proofread. 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.
proofread 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 →