Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Product Info Extractor MCP Server Extract product info from https://www.ugg.com/women-slippers/cozy-slipper/1117659.html"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
π°π· νκ΅μ΄ | πΊπΈ English
μ΄μ»€λ¨Έμ€ μΉμ¬μ΄νΈμμ μν μ 보(κ°κ²©, μ¬κ³ , μ΄λ―Έμ§, μμλ³ μ¬μ΄μ¦ λ±)λ₯Ό μλμΌλ‘ μΆμΆνλ MCP μλ²μ λλ€.
β οΈ μ€μ: DataDome κ°μ κ³ κΈ λ΄ μ°¨λ¨ μμ€ν μ μλ μ κ·Όμ μ°¨λ¨ν μ μμ΅λλ€. μ±κ³΅λ₯ μ λμ μ¬μ΄νΈμ λ€νΈμν¬ νκ²½μ λ°λΌ λ€λ¦ λλ€.
# μ μ₯μ ν΄λ‘
git clone https://github.com/elon-jang/product-info-extractor-mcp.git
cd product-info-extractor-mcp
# μλ² μμ
docker compose up -d
# ν
μ€νΈ
npm install
node test-mcp-http.js "https://www.ugg.com/women-slippers/cozy-slipper/1117659.html"npm install
npx playwright install chromium
npm run start:httpRelated MCP server: Stealth Browser MCP Server
β‘ μ΄κ³ μ: 8-10μ΄ μλ΅ (DataDome μ°ν λ‘μ§ μ κ±°λ‘ 6λ°° μ±λ₯ ν₯μ)
π κ³ μ±λ₯: λΈλΌμ°μ μΈμ€ν΄μ€ μ¬μ¬μ©μΌλ‘ νμ μμ² μ¦μ μ²λ¦¬
π₯· μ€ν
μ€ λͺ¨λ: playwright-extra + puppeteer-extra-plugin-stealthλ‘ κΈ°λ³Έ λ΄ νμ§ μ°ν
π MCP νλ‘ν μ½: Claude Desktopκ³Ό λ°λ‘ μ°λ κ°λ₯
π¦ λ©ν° νλ«νΌ: AMD64 + ARM64 (Apple Silicon & ν΄λΌμ°λ VM) μ§μ
# Ubuntu/Debian
sudo apt-get update
sudo apt-get install -y docker.io docker-compose-plugin
# RHEL/CentOS/Rocky Linux
sudo dnf install -y yum-utils
sudo dnf config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo
sudo dnf install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin
sudo systemctl start docker && sudo systemctl enable docker# Docker Composeλ‘ μ€ν (κΆμ₯)
docker compose up -d
# λλ docker runμΌλ‘ μ€ν
docker run -d -p 8080:3000 \
-e PORT=3000 -e HOST=0.0.0.0 \
--name product-info-extractor \
joomanba/product-info-extractor-mcp:latest# 컨ν
μ΄λ λ‘κ·Έ νμΈ
docker logs -f product-info-extractor
# Health check
curl http://localhost:8080/healthnpm install
node test-mcp-http.js "https://www.ugg.com/women-slippers/cozy-slipper/1117659.html"./test-server.sh http://localhost:8080claude_desktop_config.jsonμ μΆκ°:
{
"mcpServers": {
"product-info-extractor": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://localhost:8080/sse"]
}
}
}λ€μ μμ€ν λ€μ μλ μ κ·Όμ μ°¨λ¨ν μ μμ΅λλ€:
DataDome (UGG.com μ¬μ©): μ±κ³΅λ₯ μ΄ νκ²½μ λ°λΌ λ³λ
Cloudflare Advanced: μΆκ° μ°ν κΈ°λ² νμ
PerimeterX: μ°ν λ§€μ° μ΄λ €μ
β νλ‘λμ μ μΆ©λΆν ν μ€νΈ β κ°λ₯νλ©΄ 곡μ API μ¬μ© β μ¬μλ λ‘μ§ λ° μλ¬ μ²λ¦¬ ꡬν β μ±κ³΅λ₯ λͺ¨λν°λ§
# Podman μ€μΉ
sudo dnf install -y podman
# μ€ν
podman run -d -p 8080:3000 \
-e PORT=3000 -e HOST=0.0.0.0 \
--name product-info-extractor \
docker.io/joomanba/product-info-extractor-mcp:latest# Node.js v18+ μ€μΉ
curl -fsSL https://rpm.nodesource.com/setup_18.x | sudo bash -
sudo dnf install -y nodejs
# Playwright μμ‘΄μ±
sudo npx playwright install-deps
# νλ‘μ νΈ μ€μ
npm install
npx playwright install chromium
# μλ² μμ
npm run start:httpdocker buildx build --platform linux/amd64,linux/arm64 \
-t joomanba/product-info-extractor-mcp:latest --push .MIT License
Extract comprehensive product information from e-commerce URLs including images, stock availability, product variants (color-by-size inventory), price, dimensions, and specifications
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Product URL to extract information from | |
| compact | No | Enable compact mode for token optimization (87% reduction). Defaults to true. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It does convey that the tool reads product pages and returns extracted fields, which is useful. However, it does not mention output format, possible failures, limitations (e.g., non-e-commerce pages), or network behavior, leaving notable gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence efficiently states the tool's purpose and data coverage. It is front-loaded with the core action and then enumerates product aspects. Slight improvement could be a structured list, but no unnecessary words are present.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has only two parameters with full schema coverage and no output schema, so the description needs to clarify the return content. The list of extracted fields provides a solid picture of what the agent will receive, but it stops short of describing return format or edge cases. Still, it is reasonably complete for the tool's apparent simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters are already well documented. The description adds no parameter-specific semantics beyond what the schema provides; it only lists output fields, not input parameter details. This matches the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action (extract), the resource (product information from e-commerce URLs), and the scope (comprehensive data including images, stock, variants, price, dimensions, specs). No sibling tools exist, so no distinguishing is needed.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The intended use case is clear: call this tool with e-commerce product page URLs to obtain product data. There are no explicit exclusions or alternatives, but the scope is well defined by the 'e-commerce URLs' phrase, which provides sufficient usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0extract_product_infoScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap. The tool's purpose is clearly defined and distinct.
The single tool name 'extract_product_info' follows a clear verb_noun convention. Though there is only one tool, the naming is consistent with standard practices.
The server has only one tool, which falls into the borderline range. While the tool is broad and covers the stated purpose well, the count feels thin for a typical MCP server.
The tool description covers all major aspects of product information extraction: images, stock, variants, price, dimensions, and specifications. No obvious gaps exist for the stated domain.
Shopify and eBay product scraper & extractor for fast market research. Pulls Shopify products.
Stealth scraping & search. Bypasses Cloudflare, DataDome & LinkedIn via Cyborg HITL approach.
Verify live product price, currency, stock, variants and published shipping evidence for AI agents.
Fetch and extract data from any public web page, even JS-rendered or anti-bot protected