[Amazon 评论批量抓取] 翻页拉某 ASIN 的真实买家评论。可按星级/排序/媒体类型过滤。 Use when: 用户说"看一下 X 的差评""挖痛点""分析竞品评论""做 VOC""为 Listing 找用户原声"；或新品立项前差评扫描；或 listing 优化要找改进点。 Don't use: 只看 PDP 自带的几条评论摘要（用 get_amazon_product，里面已含 5-10 条 reviews 和 aiReviewsSummary，对快速判断已经够）；做关键词搜索（用 search_amazon）。 Returns: data.json[0].data.resul...
Part of the Amazon Mcp server.
Free to start. No card required.
AI agents call get_amazon_reviews 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 get_amazon_reviews 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": {
"get_amazon_reviews": {}
}
}See the full Amazon Mcp policy for all 20 tools.
These attack patterns abuse exactly the kind of access get_amazon_reviews 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 评论批量抓取] 翻页拉某 ASIN 的真实买家评论。可按星级/排序/媒体类型过滤。 Use when: 用户说"看一下 X 的差评""挖痛点""分析竞品评论""做 VOC""为 Listing 找用户原声"；或新品立项前差评扫描；或 listing 优化要找改进点。 Don't use: 只看 PDP 自带的几条评论摘要（用 get_amazon_product，里面已含 5-10 条 reviews 和 aiReviewsSummary，对快速判断已经够）；做关键词搜索（用 search_amazon）。 Returns: data.json[0].data.results[{ reviewId, date, country, star, title, content, author, authorId, authorLink, imgs[], videos, purchased, vineVoice, helpful, attributes }] — 1 页约 10 条评论。 Pair with: ↑ asin 常来自 search_amazon / get_amazon_product / list_bestsellers；↓ 评论文本可直接给 LLM 做痛点聚类、关键词提取。 Cost: 10 积点/页（贵）。建议先 pageCount=1 探一下，确认有数据再 pageCount=3~5 扩量。filterByStar='critical' 优先（差评信号密度最高）。 Tips: filterByStar 取值 = all_stars / five_star ... one_star / positive / critical；sortBy = recent (默认) | helpful；mediaType = all_contents (默认) | media_reviews_only (带图带视频，真实度更高)。. 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 get_amazon_reviews: 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.
get_amazon_reviews 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 get_amazon_reviews 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 get_amazon_reviews. 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.
get_amazon_reviews 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.