[Amazon Rufus AI 对话推荐] 用自然语言提示词问 Amazon 的 AI 购物助手 Rufus,拿回分组的结构化商品推荐 + Rufus 文本回复 + 追问建议。 Use when: 用户说"问 Amazon AI X"/"Rufus 推荐"/"用对话方式找商品"/"按场景找产品(送礼/露营/搬家/某需求)"/"开放式选品咨询"/"我不知道关键词,只知道场景"。 Don't use: 已经有明确关键词想看 SERP(用 search_amazon);想要类目热销榜(用 list_bestsellers);单 ASIN 详情(用 get_amazon_product);Go...
Part of the Amazon Mcp server.
Free to start. No card required.
AI agents call search_amazon_alexa to retrieve information from Amazon Mcp 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 search_amazon_alexa 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.
{
"version": "1",
"default": "deny",
"tools": {
"search_amazon_alexa": {}
}
}See the full Amazon Mcp policy for all 20 tools.
These attack patterns abuse exactly the kind of access search_amazon_alexa gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
[Amazon Rufus AI 对话推荐] 用自然语言提示词问 Amazon 的 AI 购物助手 Rufus,拿回分组的结构化商品推荐 + Rufus 文本回复 + 追问建议。 Use when: 用户说"问 Amazon AI X"/"Rufus 推荐"/"用对话方式找商品"/"按场景找产品(送礼/露营/搬家/某需求)"/"开放式选品咨询"/"我不知道关键词,只知道场景"。 Don't use: 已经有明确关键词想看 SERP(用 search_amazon);想要类目热销榜(用 list_bestsellers);单 ASIN 详情(用 get_amazon_product);Google 站外 AI 搜索(用 ai_search)。 Returns: data.json[{ prompt, content, products[{ title, items[{ asin,url,title,cover,score,ratingsCount,price,originalPrice,describe }] }], follow_up_questions[], screenshot }] + 顶层 taskId / url / screenshot。注意 follow_up_questions 是 snake_case(后端原样透传)。 Pair with: ↓ 拿到 asin 喂 get_amazon_product / get_amazon_reviews 深拆;follow_up_questions 可作下一轮 prompts 输入做多轮探索。 Cost: 6 积点/次调用(固定,与 prompts 条数无关)。但建议 prompts ≤3 条;>3 条响应耗时显著不稳定。平均 ~30s。. It is categorised as a Read tool in the Amazon Mcp MCP Server, which means it retrieves data without modifying state.
Register the Amazon MCP server in PolicyLayer and add a rule for search_amazon_alexa: 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 Amazon Mcp. Nothing to install.
search_amazon_alexa 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 search_amazon_alexa 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 search_amazon_alexa. 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.
search_amazon_alexa is provided by the Amazon MCP server (https://mcp.pangolinfo.com/mcp?api_key={api_key}). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 20 Amazon Mcp 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.