Skip to content

Merchgraph MCP server

io.github.marleyhereicome-cpu/merchgraphmarleyhereicome-cpustreamable-httpv1.0.1Scanned

Anime & game merch catalog: identify listings, release prices, official status, how to buy.

6 tools: 3 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 3 write, 3 read.
  • Reads private data · 0
  • Reads text others write · 2
  • Can send data out · 1
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

3 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.
Govern this server →

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 Merchgraph MCP server can do

The Merchgraph MCP server is published by the GitHub account marleyhereicome-cpu. It has 6 tools. It can create or change data (3 tools: resolve_listings_batch, estimate_landed_cost and report_correction), but cannot delete data. 3 tools only read.

2 tools bring in text other people can write (resolve_listing and discover); 1 tool can send data out of your system (resolve_listing).

The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 13, 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.

6 tools

Changes things 3Claude Code: ask
  • estimate_landed_costEstimate the total cost of buying an item in Japan and having it forwarded abroad.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
    Estimate the total cost of buying an item in Japan and having it forwarded abroad. Example: {price_jpy: 4500, sku_id: "ichiban-kuji-kh-2018-a", dest_country: "US"}. Returns routes[] (forwarding service × shipping method, with fees and total_jpy, cheapest first) and cheapest. Rough figures only: fee and shipping tables currently cover US, GB, DE and FR (other countries return no routes), come from third-party comparison guides (mid-2026) and exclude duties. Not a quote; we are not affiliated with any forwarding service.

    Annotations the server declares

    • title: Estimate cost to ship from Japan
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • report_correctionReport a mistake or missing item in the catalog (reviewed by hand before anything changes).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.
    Description, as the server wrote it
    Report a mistake or missing item in the catalog (reviewed by hand before anything changes). Example: {sku_id: "ichiban-kuji-kh-2018-a", field: "msrp_jpy", proposed_value: "750", source_url: "https://…"}. Please include a primary source (maker, official shop or reliable press) when you can. Returns {accepted, correction_id}.

    Annotations the server declares

    • title: Report a catalog mistake
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • resolve_listings_batchRun resolve_listing on up to 5 listings in one call, e.g.1 finding

    Why it is in this group

    • The name "resolve_listings_batch" says "resolve": a word for reading.
    • The description's first verb is "run": a word for a change.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Warn

      The server marks "resolve_listings_batch" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

      Matched text

      annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "resolve_listings_batch" says "resolve": a word for reading.

      What this check looks for
    Description, as the server wrote it
    Run resolve_listing on up to 5 listings in one call, e.g. when comparing search results from a marketplace. Example: {listings: [{title: "…", price_jpy: 3000}, {title: "…"}]}. Returns an array in the same order; each element has the same shape as a resolve_listing result (or {error} for that one listing only). For more than 5, split into several calls. For a single listing use resolve_listing.

    Annotations the server declares

    • title: Identify several marketplace listings
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
Only reads 3Show 3 read-only tools
  • discoverBrowse the merchandise catalog (Kingdom Hearts, Demon Slayer and One Piece) by series, character, budget and purpose.Reads text others writeNo findings

    Why it is in this group

    • The description's first verb is "browse": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "browse": it reads web pages, which anyone can write.
    Description, as the server wrote it
    Browse the merchandise catalog (Kingdom Hearts, Demon Slayer and One Piece) by series, character, budget and purpose. Use it to answer "what merch exists for X?" or "gift ideas under ¥5,000". Example: {ip: "kingdom-hearts", character: "Sora", budget_jpy: 5000, purpose: "display"}. Omit ip to search every series. Returns items[] (sku_id, name_en/name_ja, official, original price msrp_jpy plus price_local/currency, price_basis, price_note_en for per-draw prices, region, availability_hint, typical_channels, source_url, page_url = the item's page on merchgraph.app) and total_matches. For a series that is not covered, items is empty and supported_series lists the covered ones. If a character has no solo merch (e.g. Xigbar), the result also has suggested_character_group and suggested_items for their group (e.g. Organization XIII). Lists catalog entries only; it does not mean anything is for sale right now. Use explain_product with a sku_id for full details.

    Annotations the server declares

    • title: Browse the catalog
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • explain_productGet the full record for one catalog item (Kingdom Hearts, Demon Slayer and One Piece).No findings

    Why it is in this group

    • The name "explain_product" says "explain": a word for reading.
    Description, as the server wrote it
    Get the full record for one catalog item (Kingdom Hearts, Demon Slayer and One Piece). Pass a sku_id from discover/resolve_listing (e.g. {sku_id: "ichiban-kuji-kh-2018-a"}), or a free-text query such as {query: "Sora Bring Arts Halloween Town"} to get the best match. Returns names (en/ja), product line (maker, line type, release date), characters, original price (msrp_jpy, price_local, currency, price_basis), acquisition_type (retail, kuji, prize, …), availability (hint + confidence), typical_channels, shipping (whether it is only sold at shops that ship within Japan, so a shipping-forwarding service is needed from abroad; costs are not calculated; for Mercari/Suruga-ya items a note that Mercari's global app may allow direct purchase in some countries), size/weight, re-release dates, official (licensed or fan-made), verified (checked against the source), source_url (primary source) and page_url (the item's page on merchgraph.app; cite both).

    Annotations the server declares

    • title: Look up one item
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • resolve_listingIdentify a Kingdom Hearts, Demon Slayer and One Piece item from a marketplace listing (Mercari, Yahoo!Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "resolve_listing" says "resolve": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Identify a Kingdom Hearts, Demon Slayer and One Piece item from a marketplace listing (Mercari, Yahoo! Auctions, Suruga-ya, Mandarake, eBay…). Paste the listing title as-is (Japanese or English), e.g. {title: "一番くじ キングダムハーツ A賞 ソラ フィギュア 箱なし", price_jpy: 4500}. Returns candidates[] (sku_id, name_en, confidence 0-1, why, source_url, page_url = the item's page on merchgraph.app; several when the title is ambiguous), weak_matches[] when unsure, conditions[] (Japanese condition words such as 未使用/箱なし explained), flags[] (bootleg caution notes, not a verdict), price (original price and listing-to-original ratio when price_jpy is given), shipping (whether a shipping-forwarding service is needed from abroad; set platform for a precise answer; for Mercari/Suruga-ya a note that Mercari's global app may allow direct purchase in some countries), acquisition notes and next_checks_en (what to ask the seller). Listing text is not stored. For many listings at once use resolve_listings_batch.

    Annotations the server declares

    • title: Identify a marketplace listing
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

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 write2
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
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.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:21 UTC, unchanged since Nov 13, 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
3
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 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.merchgraph.app/mcp: tools/list returned 6 tools to an anonymous client, including resolve_listings_batch (write), estimate_landed_cost (write), report_correction (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 warn
  • The server marks "resolve_listings_batch" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

    Matched text

    annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "resolve_listings_batch" says "resolve": a word for reading.

    What this check looks for

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 merchgraph https://mcp.merchgraph.app/mcp
claude mcp add --transport http merchgraph https://mcp.merchgraph.app/mcp

Run 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.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__merchgraph__explain_product",
      "mcp__merchgraph__discover"
    ],
    "ask": [
      "mcp__merchgraph__resolve_listing",
      "mcp__merchgraph__resolve_listings_batch",
      "mcp__merchgraph__estimate_landed_cost",
      "mcp__merchgraph__report_correction"
    ],
    "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 merchgraph. Review it before you use it.

Capability tags behind 2 rules
  • mcp__merchgraph__resolve_listing untrusted-input, outbound
  • mcp__merchgraph__discover untrusted-input

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.marleyhereicome-cpu/merchgraph/verify?hash=e53e099d8a932305f659277f36d59a58b3ecde441a93b606fffe6d6b29ccd048" | jq -e '.changed == false'

Pinned hash e53e099d8a93, from Nov 13, 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.marleyhereicome-cpu/merchgraph/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.marleyhereicome-cpu/merchgraph
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.marleyhereicome-cpu/merchgraph.svg)](https://radar.anlyon.com/servers/io.github.marleyhereicome-cpu/merchgraph)

Source: MCP Registry · repository. Synced Nov 13, 2026, 01:17 UTC.

Merchgraph MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Merchgraph MCP server safe?

No scan can promise that. What its definitions show: 6 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Merchgraph MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Merchgraph 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 Merchgraph MCP server have?

6 tools: 3 write, 3 read. resolve_listings_batch, estimate_landed_cost, report_correction, resolve_listing, explain_product and discover.

Does the Merchgraph MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Merchgraph MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): resolve_listing.

Has the Merchgraph MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.