health__get_drug_recalls
［台灣健康資訊］查詢台灣食藥署公告的藥品回收（品名、批號、回收分級、原因）。使用者問「這個藥有沒有被回收」時使用。
This record as markdown: /tools/com-penguindriver-hub/health--get-drug-recalls.md
What health__get_drug_recalls does on AI 代理人任務中樞
AI agents call health__get_drug_recalls to retrieve information from AI 代理人任務中樞 without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
days | integer | — | 最近幾天，預設 365（有關鍵字時查全部） |
level | string | — | 回收分級，例如 第一級 |
keyword | string | — | 藥名、成分或藥廠，例如 乙醯胺酚 |
Parameters from the server's own tool schema.
Why health__get_drug_recalls is rated Low
Even though health__get_drug_recalls 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
The rule that runs health__get_drug_recalls safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AI 代理人任務中樞, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For health__get_drug_recalls, this is the rule to start with:
health__get_drug_recalls is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AI 代理人任務中樞, apply this rule, and every health__get_drug_recalls call is checked against it from then on.
Questions about health__get_drug_recalls
［台灣健康資訊］查詢台灣食藥署公告的藥品回收（品名、批號、回收分級、原因）。使用者問「這個藥有沒有被回收」時使用。. It is categorised as a Read tool in the AI 代理人任務中樞 MCP Server, which means it retrieves data without modifying state.
health__get_drug_recalls accepts 3 parameters: days, level, keyword. The full parameter table on this page comes from the server's own tool schema.
Register the AI 代理人任務中樞 MCP server in PolicyLayer and add a rule for health__get_drug_recalls: 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 AI 代理人任務中樞. Nothing to install.
health__get_drug_recalls 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 health__get_drug_recalls 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 health__get_drug_recalls. 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.
health__get_drug_recalls is provided by the AI 代理人任務中樞 MCP server (https://hub.penguindriver.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on AI 代理人任務中樞, and thousands of servers like it.
This server
Across the catalogue