shopgraph MCP server
io.github.laundromatic/shopgraphlaundromaticstreamable-httpv1.0.1Scanned
Clean product data from any URL. Schema.org + AI extraction. 200 free calls/month.
4 tools: 4 change things.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 4
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the shopgraph MCP server can do
The shopgraph MCP server is published by the GitHub account laundromatic. It has 4 tools. It can create or change data (4 tools: enrich_product, enrich_basic, enrich_html and score_product), but cannot delete data. None of its tools only reads.
4 tools bring in text other people can write (enrich_product, enrich_basic, enrich_html and 1 more); 4 tools can send data out of your system (enrich_product, enrich_basic, enrich_html and 1 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 20, 2026, version 1.0.1.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
4 tools
Changes things 4Claude Code: ask
enrich_basicExtract basic product attributes from a URL (name, price, brand, availability).Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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).Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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).Reads text others writeCan send data outNo 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.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
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.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:07 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 4
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://shopgraph.dev/mcp: tools/list returned 4 tools to an anonymous client, including enrich_product (write), enrich_basic (write), enrich_html (write), score_product (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
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/mcpclaude mcp add --transport http shopgraph https://shopgraph.dev/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .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. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as shopgraph. Review it before you use it.
Capability tags behind 4 rules
- mcp__shopgraph__enrich_product untrusted-input, outbound
- mcp__shopgraph__enrich_basic untrusted-input, outbound
- mcp__shopgraph__enrich_html untrusted-input, outbound
- mcp__shopgraph__score_product untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.laundromatic/shopgraph/verify?hash=742d0c7c61c1e267d361c0eddbf01519365962a5b53797106cae34cc0e4467fe" | jq -e '.changed == false'Pinned hash 742d0c7c61c1, from Nov 20, 2026, 01:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.laundromatic/shopgraph/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.laundromatic/shopgraph)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:38 UTC.
shopgraph MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the shopgraph MCP server safe?
- No scan can promise that. What its definitions show: 4 tools, 4 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the shopgraph MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the shopgraph MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the shopgraph MCP server have?
- 4 tools: 4 write. enrich_product, enrich_basic, enrich_html and score_product.
Does the shopgraph MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the shopgraph MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): enrich_product, enrich_basic, enrich_html and score_product.
Has the shopgraph MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 20, 2026.