Extracts structured product data from any URL and returns JSON with per-field confidence scores. You get three tools: enrich_basic for fast Schema.org parsing, enrich_product for the full pipeline with LLM fallback and headless browser rendering, and enrich_html if you already fetched the page yourself. Every field shows which extraction method produced it and how confident the system is. Set strict_confidence_threshold to auto-filter uncertain fields before they reach your agent. Outputs Universal Commerce Protocol validated JSON. Free tier gives you 50 calls per month with no signup. Useful when you need to turn messy product pages into reliable structured data for price tracking, catalog building, or comparison tools.
claude mcp add --transport http shopgraph https://shopgraph.dev/mcpRun in your terminal. Add --scope user to make it available in every project.
Review the command, arguments, and environment values before installing — MCP servers run with your local permissions.
Verified live against the running server on Jun 10, 2026.
enrich_productExtract 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).7 paramsExtract 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).
url*stringformatstringdefault · ucpdefault: defaultforce_refreshbooleaninclude_scorebooleanpayment_method_idstringminimum_confidencenumberstrict_confidence_thresholdnumberenrich_basicExtract 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.7 paramsExtract 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.
url*stringformatstringdefault · ucpdefault: defaultforce_refreshbooleaninclude_scorebooleanpayment_method_idstringminimum_confidencenumberstrict_confidence_thresholdnumberenrich_htmlExtract 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).8 paramsExtract 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).
url*stringhtml*stringformatstringdefault · ucpdefault: defaultforce_refreshbooleaninclude_scorebooleanpayment_method_idstringminimum_confidencenumberstrict_confidence_thresholdnumberscore_productExtract 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.4 paramsExtract 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.
url*stringformatstringdefault · ucpdefault: defaultpayment_method_idstringstrict_confidence_thresholdnumbercom.mcparmory/google-sheets
domdomegg/google-sheets-mcp
henilcalagiya/google-sheets-mcp
cct15/war-dashboard-data
moooonad/mcp-google-sheets-full
io.github.br0ski777/csv-to-json