Skip to main content
Glama
pangolinfo

Amazon All-in-One Scrape MCP

Official

scrape_url

Scrapes Amazon pages not covered by specialized tools. Provide either a bare content (keyword, ASIN, nodeId) or a full URL with custom filters, sorting, or pagination. Requires matching parserName.

Instructions

[通用 Amazon 抓取 — 高级逃生口] 抓 5 个专用工具覆盖不到的页面。两种喂法二选一: ① content=裸零件(关键词/nodeId/sellerId/ASIN)+ site,后端按 parserName 自动拼基础 URL。content 模式不带筛选/排序/翻页 —— 只是裸零件。用户/AI 通常只有零件,简单页用这个最省事。 ② url=完整 Amazon 链接,任何筛选/排序/翻页都拼进这个 url(content 模式做不到的全靠它)。筛选语法举例:价格 $25-50 → '/s?k=earbuds&low-price=25&high-price=50';按评论数排序 → '&s=review-rank';翻页 → '&page=2';类目+价格 → '/s?i=aps&rh=n%3A172282&fs=true&low-price=25'。 Use when: 普通工具拼不出目标 URL —— "搜 X 但只要 $25-50""按评论排序的结果""类目按价格筛";或用户已有一个具体 Amazon 链接要抓。要带筛选就走 url 模式。 Don't use: 能用专用工具就别用 —— 纯关键词搜索用 search_amazon、单 ASIN 用 get_amazon_product、卖家用 list_seller_products、类目榜单用 list_bestsellers/list_new_releases。 Returns (format='json'): data.json[0].data.{ ... results[] ... },结构随 parserName 而定。⚠️ content/url 与 parserName 不匹配 → 后端返回 data.{ status_code, rawHtml, url }(未解析)。 Pair with: ↓ 拿到 asin 喂 get_amazon_product / get_amazon_reviews。 Cost: ~1 积点/次, ~5s。 ⚠️ content 和 url 二选一(都传或都不传会报错);带筛选/翻页必须用 url 模式;parserName 必须和页面类型匹配。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
parserNameYes解析器名,决定后端怎么解析页面 + 怎么从 content 拼 URL。必须和页面类型匹配:amzKeyword=关键词搜索(content=关键词)/ amzProductOfCategory=类目商品(content=nodeId)/ amzProductOfSeller=卖家店铺(content=sellerId)/ amzProductDetail=单品(content=ASIN)/ amzBestSellers / amzNewReleases / amzReviewV2=评论 / amzFollowSeller=跟卖 / amzVariantAsin=变体。
contentNo裸零件(后端按 parserName 自动拼 URL)。传这个**或** url 二选一。Examples: 'wireless earbuds'(amzKeyword)/ '172282'(amzProductOfCategory 的 nodeId)/ 'ATVPDKIKX0DER'(amzProductOfSeller 的 sellerId)/ 'B09B8V1LZ3'(amzProductDetail 的 ASIN)。用户/AI 通常只有零件,优先用这个。
urlNo完整 Amazon URL(https://)。传这个**或** content 二选一。用于你已经有一个现成链接(如浏览器复制的带筛选/排序的搜索结果页)。Example: 'https://www.amazon.com/s?k=earbuds&rh=p_36%3A2500-5000&s=review-rank'。必须和 parserName 匹配。
siteNoAmazon 站点(content 模式下后端据此选域名拼 URL)。默认 amz_us。url 模式下可省略(url 已含域名)。amz_us
formatNo返回格式。默认 'json'(结构化 results);需要原始页面阅读时切 'markdown'。json
zipcodeNo邮编,必须匹配 site 所在国家。可选;不传时后端随机挑一个。
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but the description fully compensates by detailing behavioral traits: two mutually exclusive modes, parserName matching requirement, error behavior (rawHtml return), cost per call (~1 credit), and approximate duration (~5s).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is fairly long but well-structured with bulleted lists, examples, and clear sections. It earns each sentence with useful information, though a minor reduction in verbosity could improve conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, 3 enums, no output schema) and the need to cover two modes, the description is thorough: covers both modes, error cases, cost, pairing, and filter syntax. No gaps identified.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, yet the description adds significant extra meaning: explains the relationship between parserName and content, provides concrete examples for each parameter, clarifies that url mode supports filters not possible with content, and gives filter syntax demos. This goes well beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool as a general-purpose Amazon scraper for pages not covered by five dedicated tools, and explains two distinct modes (content and url) with specific use cases. It explicitly names sibling tools to differentiate.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'Use when' and 'Don't use' sections listing specific scenarios and alternative tools. Also gives filter syntax examples and pairing advice, leaving no ambiguity about when to invoke this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pangolinfo/pangolinfo-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server