[Amazon 利基筛选] 按 50+ 维指标筛选 Amazon Niche（比类目更细的"消费需求簇"），或当作"niche 详情"接口取单个 niche 完整深度报告。 Use when: 用户说"找蓝海""高搜索量低竞争的利基""增长快的小众市场""niche 选品""为这个 niche 出详细报告""退货率低的利基""退货率 < 10% 的市场"；GTM 选品 SOP 的核心筛选步骤；要某个 niche 的费用结构 / 品牌年龄 / 新品上架趋势等深度指标。 Don't use: 想筛整类目（用 filter_categories）；想看 niche 下的具体商品（用 list_...
Risk signalsHigh parameter count (23 properties)
Part of the Amazon Mcp server.
Free to start. No card required.
AI agents call filter_niches 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 filter_niches 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": {
"filter_niches": {}
}
}See the full Amazon Mcp policy for all 20 tools.
These attack patterns abuse exactly the kind of access filter_niches 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 利基筛选] 按 50+ 维指标筛选 Amazon Niche（比类目更细的"消费需求簇"），或当作"niche 详情"接口取单个 niche 完整深度报告。 Use when: 用户说"找蓝海""高搜索量低竞争的利基""增长快的小众市场""niche 选品""为这个 niche 出详细报告""退货率低的利基""退货率 < 10% 的市场"；GTM 选品 SOP 的核心筛选步骤；要某个 niche 的费用结构 / 品牌年龄 / 新品上架趋势等深度指标。 Don't use: 想筛整类目（用 filter_categories）；想看 niche 下的具体商品（用 list_category_products 配合 categoryId，niche 自带的样品 ASIN 只有 1 个 referenceAsin）；只想要广义关键词搜索（用 search_amazon）。 Returns: data.items.data[{ nicheId, nicheTitle, referenceAsinImageUrl, currency, searchVolumeT90, searchVolumeT360, searchVolumeGrowthT90, minimumPrice, maximumPrice, avgPrice, productCount, sponsoredProductsPercentage, primeProductsPercentage, top5ProductsClickShare, top20BrandsClickShare, brandCount, sellingPartnerCount, avgBrandAge, avgBestSellerRank, avgProductPrice, avgReviewCount, avgReviewRating, avgDetailPageQuality, newProductsLaunchedT180/T360, successfulLaunchesT90/T180/T360, returnRateT360, 各项费用 T365 ... 100+ 字段 }] + data.items.pagination.{ total, page, size, hasNext }。翻页: 用 page 参数（默认 1，从 1 开始，size 上限 10(默认 3)）；pagination.hasNext=true 表示还有下一页，hasNext=false 表示已到底。 Pair with: ↑ 必填 marketplaceId（默认 US）；nicheTitle 关键词过滤，nicheId 单 niche 详情；↓ 拿到 referenceAsin 后喂 get_amazon_product 看代表品；niche 不直接关联 categoryId，需要二次推断。 Cost: ~1 积点/次, ~5s。 Tips: size 上限 10(默认 3)；50+ 长尾筛选字段走 extraFilters 透传；典型蓝海过滤组合 = searchVolumeT90Min 高 + top5ProductsClickShareT360Max 低 + productCountMax 中 + searchVolumeGrowthT90Min > 0 + returnRateT360Max ≤ 0.10（低退货）。退货率筛选用 returnRateT360Max（上限，0-1 小数），返回里 returnRateT360 字段直接给出具体退货率。. 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 filter_niches: 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.
filter_niches 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 filter_niches 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 filter_niches. 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.
filter_niches 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.