AI agents call hunter_batch_task_result_download to retrieve information from Hunter without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and downloads data (batch query results) to a local system. While download operations involve data transfer, the core function is read-only retrieval of existing export results from a completed batch task. No data is created, modified, deleted, or executed - it simply fetches and downloads CSV results.
From the tool's definition Tool description indicates it 'downloads...export file (CSV format), save to local' - a retrieval operation that fetches previously generated query results.
Attacks that exploit this kind of access
下载 Qianxin Hunter 批量查询的导出文件（CSV格式），保存到本地。注意：需先使用 hunter_batch_task_progress 确认任务已完成。. It is categorised as a Read tool in the Hunter MCP Server, which means it retrieves data without modifying state.
Register the Hunter MCP server in PolicyLayer and add a rule for hunter_batch_task_result_download: 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 Hunter. Nothing to install.
hunter_batch_task_result_download 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 hunter_batch_task_result_download 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 hunter_batch_task_result_download. 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.
hunter_batch_task_result_download is provided by the Hunter MCP server (piggyhurry/hunter-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 →