Interact with Kagi AI Assistant for conversations and questions. Supports multiple AI models and can maintain conversation context across multiple exchanges. Provides access to current information through internet connectivity. Required environment variables: - KAGI_SESSION_TOKEN: Your Kagi sessi...
AI agents call kagi_assistant to retrieve information from Kagi MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though kagi_assistant only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Interact with Kagi AI Assistant for conversations and questions. Supports multiple AI models and can maintain conversation context across multiple exchanges. Provides access to current information through internet connectivity. Required environment variables: - KAGI_SESSION_TOKEN: Your Kagi session token - KAGI_SEARCH_COOKIE: Your _kagi_search_ cookie value - KAGI_MODEL_LIST: Comma-separated list of available models (e.g.,. It is categorised as a Read tool in the Kagi MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Kagi MCP Server MCP server in PolicyLayer and add a rule for kagi_assistant: 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 MCP Server. Nothing to install.
kagi_assistant 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 kagi_assistant 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 kagi_assistant. 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.
kagi_assistant is provided by the Kagi MCP Server MCP server (z23cc/kagi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.