Coreplex MCP server
ai.coreplex/shoppingcoreplex.aistreamable-httpv1.0.0Scanned
Search, compare prices and find official stores across brands that sell on Shopify.
7 tools: 7 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- 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 Coreplex MCP server can do
The Coreplex MCP server is published by coreplex.ai, a domain the MCP Registry verified. It has 7 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
None of its tools reads private data, brings in text other people write, or sends data out.
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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 11, 2026, version 1.0.0.
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.
7 tools
Only reads 7Show 7 read-only tools
compare_pricesWho else sells this exact item, each priced for the same option — matched on Shopify catalog id or barcode, so a cheaper seller is a real match rather than a lookalike.No findings
Why it is in this group
- The name "compare_prices" says "compare": a word for reading.
Description, as the server wrote it Who else sells this exact item, each priced for the same option — matched on Shopify catalog id or barcode, so a cheaper seller is a real match rather than a lookalike. Resellers are labelled and similar listings are kept apart from price matches. Pass variant_id (from get_product) for a multi-option product. Examples: "who else sells this exact Owala bottle", "is the official store actually cheaper".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
find_health_productsProducts whose seller states a third-party testing or eligibility claim — HSA/FSA eligible, USP Verified, NSF, Informed Sport, GMP facility, ConsumerLab — matched against the selle…No findings
Why it is in this group
- The name "find_health_products" says "find": a word for reading.
Description, as the server wrote it Products whose seller states a third-party testing or eligibility claim — HSA/FSA eligible, USP Verified, NSF, Informed Sport, GMP facility, ConsumerLab — matched against the seller's own text and returned with the claim marked seller-stated. Examples: "HSA/FSA eligible vitamin D", "NSF certified protein powder", "USP verified magnesium".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_passportA product passport: the brand's own listing, then every other store found carrying it, each marked same item, likely same, other version, bundle or accessory, with the evidence for…No findings
Why it is in this group
- The name "get_passport" says "get": a word for reading.
Description, as the server wrote it A product passport: the brand's own listing, then every other store found carrying it, each marked same item, likely same, other version, bundle or accessory, with the evidence for that call. This is the only place a reseller is identified rather than guessed. Examples: "is this seller an authorized reseller", "which stores carry the exact same jacket".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_productOne listing in full: the price of every option, stock, the seller, whether that seller is the brand's own official store, and the seller's policy links.No findings
Why it is in this group
- The name "get_product" says "get": a word for reading.
Description, as the server wrote it One listing in full: the price of every option, stock, the seller, whether that seller is the brand's own official store, and the seller's policy links. Use product_id from search_products. Don't construct URLs. Examples: "what every size of the FreeSip costs", "is this sold by the brand itself".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_return_policyThe seller's own return terms — window, condition, opened items, who pays return shipping — quoted as the exact sentences of the policy that applies to this listing, not a generic …No findings
Why it is in this group
- The name "get_return_policy" says "get": a word for reading.
Description, as the server wrote it The seller's own return terms — window, condition, opened items, who pays return shipping — quoted as the exact sentences of the policy that applies to this listing, not a generic template. Examples: "can I return opened supplements", "return window for a stroller".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_brandsBrands with a confirmed official Shopify store.No findings
Why it is in this group
- The name "list_brands" says "list": a word for reading.
Description, as the server wrote it Brands with a confirmed official Shopify store. Supplement brands are listed first, then every other category, each with its own store domain. Paged: returns total, next_cursor and a line stating catalog coverage. Examples: "which supplement brands do you carry", "beauty brands with official stores", "everything you cover".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
search_productsFind a product across brands that sell on Shopify, with the seller named and the brand's own official store flagged — what a plain product search cannot tell you.No findings
Why it is in this group
- The name "search_products" says "search": a word for reading.
Description, as the server wrote it Find a product across brands that sell on Shopify, with the seller named and the brand's own official store flagged — what a plain product search cannot tell you. Every result carries product_id, product_url, price per option and stock. Examples: "magnesium powders with third-party testing", "official store for Owala", "wearable breast pump".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- 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 or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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, 18:25 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
- 0
- 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
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.
Tools7 changed.~7 changedView diff
- Changed:compare_pricesOnly readsdescriptioninputSchema
- Changed:find_health_productsOnly readsdescription
- Changed:get_passportOnly readsdescriptioninputSchema
- Changed:get_productOnly readsdescriptioninputSchema
- Changed:get_return_policyOnly readsdescriptioninputSchema
- Changed:list_brandsOnly readsdescriptioninputSchema
- Changed:search_productsOnly readsdescription
Tools2 changed.~2 changedView diff
- Changed:compare_pricesOnly readsdescriptioninputSchema
- Changed:get_passportOnly readsdescription
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http shopping https://coreplex.ai/api/apps/6a9567482e969b1ab43e0c49/functions/coreplexMcpclaude mcp add --transport http shopping https://coreplex.ai/api/apps/6a9567482e969b1ab43e0c49/functions/coreplexMcpRun 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": [
"mcp__shopping__search_products",
"mcp__shopping__get_product",
"mcp__shopping__get_return_policy",
"mcp__shopping__compare_prices",
"mcp__shopping__get_passport",
"mcp__shopping__list_brands",
"mcp__shopping__find_health_products"
],
"ask": [],
"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 shopping. Review it before you use it.
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/ai.coreplex/shopping/verify?hash=14c5bb0af3e4843d0c3816ccb7f1251cbeaab061840f63a26e02856bc7c5f94e" | jq -e '.changed == false'Pinned hash 14c5bb0af3e4, from Nov 11, 2026, 18:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.coreplex/shopping/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.coreplex/shopping)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
Coreplex MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Coreplex MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the Coreplex MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Coreplex 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 Coreplex MCP server have?
- 7 tools: 7 read. search_products, get_product, get_return_policy, compare_prices, get_passport, list_brands and find_health_products.
Does the Coreplex MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Coreplex MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Coreplex MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 11, 2026. Every change is on this page and in its Atom feed.