AI agents call assess_growth to retrieve information from Groowooth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
assess_growth retrieves and computes growth assessment statistics from provided data without creating, modifying, deleting, or executing external operations. It is a read-only analytical tool that interprets child growth metrics against established standards.
From the tool's definition Tool performs assessment and returns z-scores, percentiles, and range labels based on WHO/China NHC standards. The description explicitly states it provides 'statistical language, not clinical diagnosis' and returns computed metrics without modifying any data.
Attacks that exploit this kind of access
基于 WHO 或中国卫健委标准评估儿童生长发育，返回各 indicator 的 z-score、百分位、范围标签（统计语言，不含临床诊断）. It is categorised as a Read tool in the Groowooth MCP Server, which means it retrieves data without modifying state.
Register the Groowooth MCP server in PolicyLayer and add a rule for assess_growth: 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 Groowooth. Nothing to install.
assess_growth 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 assess_growth 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 assess_growth. 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.
assess_growth is provided by the Groowooth MCP server (xiaot945/groowooth). 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 →