Low Risk

recommend

根据用户画像推荐保险方案(核心工具)。信息不全也可调用——返回最佳推荐+缺失字段提示。传入health_conditions自动附带核保结论。默认纯数据模式(<100ms),设include_reasoning:true生成自然语言理由(+3s)。

Risk signalsHigh parameter count (10 properties)

Part of the WhyLingxi 保险顾问 Insurance Advisor server.

recommend is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE WHYLINGXI 保险顾问 INSURANCE ADVISOR →

Free to start. No card required.

AI agents call recommend to retrieve information from WhyLingxi 保险顾问 Insurance Advisor without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though recommend only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "recommend": {}
  }
}

See the full WhyLingxi 保险顾问 Insurance Advisor policy for all 9 tools.

Get this rule live on your own WhyLingxi 保险顾问 Insurance Advisor server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY WHYLINGXI 保险顾问 INSURANCE ADVISOR →

View all 9 tools →

These attack patterns abuse exactly the kind of access recommend gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so recommend only ever does what you allow.

SECURE WHYLINGXI 保险顾问 INSURANCE ADVISOR →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the recommend tool do? +

根据用户画像推荐保险方案(核心工具)。信息不全也可调用——返回最佳推荐+缺失字段提示。传入health_conditions自动附带核保结论。默认纯数据模式(<100ms),设include_reasoning:true生成自然语言理由(+3s)。. It is categorised as a Read tool in the WhyLingxi 保险顾问 Insurance Advisor MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recommend? +

Register the WhyLingxi 保险顾问 Insurance Advisor MCP server in PolicyLayer and add a rule for recommend: 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 WhyLingxi 保险顾问 Insurance Advisor. Nothing to install.

What risk level is recommend? +

recommend is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit recommend? +

Yes. Add a rate_limit block to the recommend 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.

How do I block recommend completely? +

Set action: deny in the PolicyLayer policy for recommend. 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.

What MCP server provides recommend? +

recommend is provided by the WhyLingxi 保险顾问 Insurance Advisor MCP server (https://whylingxi.cn/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every WhyLingxi 保险顾问 Insurance Advisor tool call.

Deterministic rules across all 9 WhyLingxi 保险顾问 Insurance Advisor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.