AI agents call deep-search-create-task to retrieve information from Ufn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though deep-search-create-task 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
创建深度搜索异步任务，立即返回task_id. It is categorised as a Read tool in the Ufn MCP Server, which means it retrieves data without modifying state.
Register the Ufn MCP server in PolicyLayer and add a rule for deep-search-create-task: 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 Ufn. Nothing to install.
deep-search-create-task 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 deep-search-create-task 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 deep-search-create-task. 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.
deep-search-create-task is provided by the Ufn MCP server (@unifuncs/ufn-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.