Shopgraph
About
AI shopping agents need structured product data to compare prices, check availability, and make decisions. Shopify Catalog covers Shopify merchants. Google UCP covers Google Shopping. ShopGraph covers everything else — the DTC brands, independent retailers, and niche suppliers th
Details
- Author
- laundromatic
- Downloads
- 360
- Categories
- Web Scraping, Other, AI
Jump to
- Schema.org extraction with 0.95 confidence
- Gemini LLM fallback for pages without structured data
- Pay-per-call billing via Stripe MPP
- Cached results returned free (24‑hour TTL)
- Playwright browser fallback for JS‑rendered or bot‑blocked pages
- Two tools: enrich_product ($0.02) and enrich_basic ($0.01)
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
ShopgraphCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install with npm install, set STRIPE_TEST_SECRET_KEY and GOOGLE_API_KEY in .env, then build and run via npm start (stdio) or npm run start:http (HTTP). Agents connect via MCP and call enrich_product or enrich_basic with a URL and optional payment_method_id.
enrich_product
Extract comprehensive product data from a URL including name, price, brand, images, availability, and more. Uses schema.org structured data when available, with LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
enrich_basic
Extract basic product attributes from a URL (name, price, brand, availability). Faster and cheaper than enrich_product. 50 free calls/month — no payment needed. Paid: $0.01 per call after free tier. Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
enrich_html
Extract product data from raw HTML you already have (no HTTP fetch needed). Ideal when using Bright Data, Firecrawl, or any scraping API — pipe the HTML through ShopGraph for structured product data. Uses schema.org + LLM fallback. Costs $0.02 per call (cached results are free). Each field carries verification metadata in _shopgraph: provenance (field_method — which source/tier produced it: schema_org, llm, or hybrid), freshness (field_freshness — recency + volatility_class, for volatile fields like price & availability), and abstain (a field is null when ShopGraph cannot verify it on the page). Rely on provenance, freshness, and the abstain signal to decide what to trust.
score_product
Extract product data and return agent-readiness score (0-100). Scores structured data completeness, semantic richness, UCP compatibility, pricing clarity, and inventory signals. Full scoring breakdown included.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"shopgraph": {
"shopgraph": {
"type": "url",
"url": "https://shopgraph.dev/mcp"
}
}
}
}McpServers
{
"shopgraph": {
"type": "url",
"url": "https://shopgraph.dev/mcp"
}
}@laundromatic/shopgraph
Structured product data from the open web, where platform APIs don't reach. Schema.org + AI extraction. Pay per call via Stripe MPP.
Website: https://shopgraph.dev | MCP Endpoint: https://shopgraph.dev/mcp
What it does
Agents connect via Model Context Protocol and call enrichment tools to extract structured product data from URLs. Requests are payment-gated via Stripe: unauthenticated calls receive a 402 challenge, authenticated calls with a payment_method_id are processed and billed.
Architecture
Agent → MCP (streamable-http) → enrich_product / enrich_basic
→ Cache hit? Return immediately (free)
→ No payment_method_id? Return 402 + MPP challenge
→ Payment confirmed → schema.org extraction (fast, 0.95 confidence)
→ No structured data? → Gemini LLM fallback (0.7+ confidence)
→ Bot-blocked or JS-rendered? → Playwright browser fallback
→ Return ProductData + PaymentReceipt
Setup
npm install
Required environment variables in .env:
| Variable | Purpose |
|----------|---------|
| STRIPE_TEST_SECRET_KEY | Stripe test mode secret key |
| GOOGLE_API_KEY | Gemini API key for LLM fallback |
Note: Check .env for duplicate key definitions — dotenv uses the last occurrence.
Build & Run
npm run build # Compile TypeScript
npm start # Run MCP server (stdio)
npm run start:http # Run HTTP server (for Vercel/remote)
npm run dev # Run with tsx (no build needed)
Test
npm run test:run # Run all tests once
npm test # Run tests in watch mode
Tools
| Tool | Price | Description |
|------|-------|-------------|
| enrich_product | $0.02 | Full product data extraction |
| enrich_basic | $0.01 | Basic attributes only (no images) |
Cached results are returned free of charge (24-hour TTL).
MCP Configuration
Add to your MCP client config:
{
"mcpServers": {
"shopgraph": {
"command": "node",
"args": ["/path/to/shopgraph/dist/index.js"]
}
}
}
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
