Skip to content

io.github.laundromatic/shopgraph

by laundromatic · remote · local (npm) · no sign-in to list tools · v1.0.1 · published by GitHub user laundromatic

Clean product data from any URL. Schema.org + AI extraction. 200 free calls/month.

Changes · 4
CompareRegistry entry

4 tools: 4 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http shopgraph https://shopgraph.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 4Claude Code: ask
  • enrich_basicExtract basic product attributes from a URL (name, price, brand, availability).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • enrich_htmlExtract product data from raw HTML you already have (no HTTP fetch needed).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • enrich_productExtract comprehensive product data from a URL including name, price, brand, images, availability, and more.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
  • score_productExtract product data and return agent-readiness score (0-100).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http shopgraph https://shopgraph.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__shopgraph__enrich_product",
      "mcp__shopgraph__enrich_basic",
      "mcp__shopgraph__enrich_html",
      "mcp__shopgraph__score_product"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as shopgraph. Review it before you use it.