Skip to main content
Glama
deenesjakoruzh
ChocoData-com

amazon-scraper-api

by ChocoData-com
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

amazon-scraper-api-mcp

npm npm downloads license

Amazon Scraper API용 MCP(Model Context Protocol) 서버입니다. Claude Desktop, Cursor, Claude Code, Continue 또는 기타 MCP 호환 AI 클라이언트에 연결할 수 있습니다. 모델이 일급 도구 호출(first-class tool call)로서 실시간 Amazon 제품 데이터를 사용할 수 있게 해줍니다.

이 도구로 가능한 작업

"amazon.com에서 평점이 가장 높은 150달러 미만의 무선 이어버드를 찾아줘. 그 다음 amazon.de에서 더 저렴한지 확인해줘."

이것은 하나의 프롬프트로 가능합니다. MCP가 없으면 AI는 Amazon 페이지를 가져올 수 없으며(Amazon은 LLM 브라우징을 차단함) 가격과 재고에 대한 최신 정보를 전혀 알 수 없습니다. 이 MCP 서버를 사용하면 amazon_search 및 amazon_product를 직접 호출하여 Amazon Scraper API에서 구조화된 데이터를 가져올 수 있습니다.

Related MCP server: Amazon Price Tracker MCP

제공되는 도구

도구

기능

일반적인 용도

amazon_product

ASIN 또는 URL로 단일 제품 가져오기

"B09HN3Q81F의 가격과 평점 가져오기"

amazon_search

정렬/필터링을 포함한 키워드 검색

"50달러 미만의 상위 10개 무쇠 프라이팬"

amazon_batch_create

비동기 스크래핑을 위해 최대 1000개의 ASIN 대기열에 추가

"내 카탈로그에 있는 500개 제품 모두 스크래핑하고 완료되면 웹훅 보내기"

amazon_batch_status

배치 작업 진행 상황 확인

"배치 xyz가 얼마나 완료되었나요?"

각 도구는 제목, 가격, 평점, 리뷰 수, 재고 여부, 구매 상자(buybox), 옵션, 이미지, 주요 특징, 카테고리, 사양 표와 같은 구조화된 JSON을 반환합니다.

벤치마크 (실제 운영 환경, 2026-04)

지표

값

중앙값 지연 시간 (제품, 미국)

~2.6초

P95 지연 시간

~6초

가격 / 1,000회 요청

$0.50 (고정)

마켓플레이스

20개 이상

Claude Desktop 설정

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) 또는 %APPDATA%\Claude\claude_desktop_config.json (Windows)을 편집하세요:

{
  "mcpServers": {
    "amazon-scraper": {
      "command": "npx",
      "args": ["-y", "amazon-scraper-api-mcp"],
      "env": {
        "ASA_API_KEY": "asa_live_..."
      }
    }
  }
}

Claude Desktop을 다시 시작하세요. 채팅 작성기의 MCP 아이콘 아래에 도구가 나타납니다.

Cursor 설정

설정 → MCP → 서버 추가:

  • 명령어: npx -y amazon-scraper-api-mcp

  • 환경 변수: ASA_API_KEY=asa_live_...

Claude Code 설정

claude mcp add amazon-scraper -- npx -y amazon-scraper-api-mcp
# then set ASA_API_KEY in the environment Claude Code runs in

대화 예시 (Claude Desktop)

사용자: amazon.com에서 AirPods Pro 3세대 현재 가격이 얼마인가요?

Claude: [ASIN B09HN3Q81F로 amazon_product 호출]

AirPods Pro 3세대는 현재 amazon.com에서 $199.00이며, 기존 $249.00에서 할인된 가격(20% 할인)입니다. 58,214개의 리뷰에서 4.7점의 평점을 받았으며, 재고가 있고 Amazon.com에서 직접 배송 및 판매하며 Prime 서비스가 적용됩니다.

사용자: 독일 Amazon 목록과 비교해줘.

Claude: [query=B09HN3Q81F, domain=de로 amazon_product 호출]

amazon.de에서 동일한 제품은 229.00 EUR에 등록되어 있습니다. 오늘 환율로 계산하면 약 $245이며, 미국 가격보다 약 23% 더 비쌉니다. 독일 목록은 Amazon에서 배송하며 Prime 배송 자격이 있습니다.

일반적인 "웹 브라우징" MCP와 다른 점

amazon.com을 로드하려는 일반적인 브라우저 도구는 일반적으로 차단(로봇 확인)되거나 모바일용으로 간소화된 페이지를 제공합니다. 이 서버는 모든 호출을 Amazon Scraper API를 통해 라우팅하며, 다음과 같은 이점이 있습니다:

  • 로봇/CAPTCHA 페이지를 감지하고 단계별 프록시 계층을 통해 재시도

  • HTML이 아닌 구조화된 JSON(타입이 지정된 필드) 반환

  • 국가별 주거용 IP를 사용하여 20개 이상의 마켓플레이스 지원

  • 웹훅 전달을 통해 배치(수백에서 수천 개의 ASIN) 처리

  • 내장된 속도 제한 백오프(rate-limit backoff)

오류 처리

오류는 code 필드와 힌트가 포함된 도구 오류로 모델에 전달됩니다. 모델은 하위 작업을 재시도할지 포기할지 결정합니다. 사용자가 직접 오류 처리 로직을 작성할 필요가 없습니다.

일반적인 코드: INVALID_API_KEY, INSUFFICIENT_CREDITS, RATE_LIMITED, target_unreachable, amazon-robot-or-human, extraction_failed, SERVICE_OVERLOADED. 전체 표: amazonscraperapi.com/docs/errors.

API 키 받기

app.amazonscraperapi.com. 가입 시 1,000회 무료 요청 제공, 신용카드 불필요. 이 MCP가 제공하는 모든 도구를 테스트하고 수십 번의 생산적인 대화를 나누기에 충분합니다.

링크

라이선스

MIT

Available Tools

4 tools
amazon_batch_createA

Queue up to 1000 ASINs or search queries for async processing. Returns a batch id - poll with amazon_batch_status or receive a webhook callback.

ParametersJSON Schema
NameRequiredDescriptionDefault
endpointYes
itemsYes
webhook_urlNoOptional HTTPS callback URL

TDQS

A3.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden. It mentions async processing and result retrieval methods, but lacks details on side effects, auth, rate limits, or error handling. The description is insufficient for a tool with no structured behavioral hints.

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

Conciseness5/5

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

The description is a single, well-structured sentence that front-loads the purpose and includes key details (limit, result method). No extraneous words.

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

Completeness3/5

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

Given missing annotations and output schema, the description covers main function and result retrieval. However, it lacks details on error handling, item validation, and batch id format. Adequate but with gaps.

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

Parameters3/5

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

Schema coverage is 33%, only webhook_url has a description. The description adds context for items ('ASINs or search queries') but does not explain endpoint values or items structure beyond the schema. It partially compensates but not fully.

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 queues up to 1000 ASINs or search queries for async processing and returns a batch id. It distinguishes from siblings like amazon_batch_status (poll), amazon_product, and amazon_search (single lookups).

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

Usage Guidelines3/5

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

The description implies use for multiple items ('up to 1000 ASINs or search queries') and mentions polling or webhook, but does not explicitly state when to avoid this tool (e.g., for single queries) or contrast with siblings.

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

amazon_batch_statusB

Poll an async batch job for progress + results.

ParametersJSON Schema
NameRequiredDescriptionDefault
idYes

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations provided, the description must disclose behavioral traits. It indicates a read-only polling operation, but does not mention safety, rate limits, or whether it blocks or returns immediately. Adequate but minimal.

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

Conciseness5/5

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

A single sentence with no fluff, front-loaded with the action verb 'Poll'. Every word is necessary.

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

Completeness3/5

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

The description is adequate for a simple polling tool, but lacks context on return values (no output schema) and lifecycle (e.g., relationship to batch creation). More detail would improve completeness.

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

Parameters2/5

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

The only parameter 'id' has no description in the schema (0% coverage) and the description does not explain what it represents (e.g., the job ID from amazon_batch_create). The description fails to add meaning 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 uses a specific verb 'Poll' and resource 'async batch job', and specifies that it returns 'progress + results'. This clearly distinguishes it from sibling tools like amazon_batch_create (creation) and unrelated searches.

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

Usage Guidelines2/5

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

No guidance is provided on when to use this tool versus alternatives, such as indicating that it should be called after creating a batch job with amazon_batch_create, or any prerequisites or polling behavior.

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

amazon_productB

Fetch structured data for a single Amazon product by ASIN. Returns ~55 fields including title, price, variations, reviews, category ladder, images.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes10-character Amazon ASIN, e.g. "B09HN3Q81F"
domainNoAmazon marketplace TLDcom
languageNoContent language xx_YY (e.g. en_US, de_DE). Not all combos supported per marketplace.

TDQS

B3.4/5.0
Behavior2/5

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

No annotations provided; description leaves burden on text. States return fields but omits idempotency, rate limits, authentication needs, or any side effects. For a fetch tool, read-only behavior is implied but not explicit.

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?

Single sentence is efficient and front-loaded with action 'Fetch structured data'. No wasted words.

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

Completeness3/5

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

With 3 parameters and no output schema, description mentions ~55 fields and examples. Lacks error handling, response format, or data shape beyond field list.

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

Parameters3/5

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

Schema covers all parameters, description adds no extra meaning beyond 'by ASIN'. Baseline 3 applies due to full schema coverage.

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?

Description clearly states verb 'Fetch', resource 'structured data for a single Amazon product', and identifier 'by ASIN'. Lists sample fields, distinguishing from sibling batch and search tools.

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

Usage Guidelines3/5

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

Implicitly for single product lookup by ASIN, but no explicit comparison with sibling tools (amazon_search, amazon_batch_*). Lacks when-not-to-use or alternative guidance.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 4 tool updatesv0.1.5
    • First observedamazon_batch_create
    • First observedamazon_batch_status
    • First observedamazon_product
    • First observedamazon_search
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.8/5.0

Scored across 4 tools

Disambiguation5/5

Each tool has a clearly distinct purpose: batch creation, batch status polling, single product fetch, and keyword search. No overlap between tools.

Naming Consistency4/5

All tools use snake_case and start with 'amazon_'. Three follow verb_noun pattern ('batch_create', 'batch_status', 'search'), while 'amazon_product' is a noun implying fetch. Minor inconsistency but overall predictable.

Tool Count5/5

Four tools cover the essential scraping operations: search, single product details, and async batch processing. The count is well-scoped for the server's purpose.

Completeness4/5

Covers search, single product, and batch processing. Missing dedicated review or category tools, but the product tool includes reviews. Minor gaps but core workflows are complete.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers