brands MCP server
by.authorized/brandsauthorized.bystreamable-httpv2.0.1Scanned
Search brands, find authorized retailers and verify a shop's authorization on authorized.by
7 tools: 1 change things and 6 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 brands MCP server can do
The brands MCP server is published by authorized.by, a domain the MCP Registry verified. It has 7 tools. It can create or change data (1 tool: verify_retailer_authorization), but cannot delete data. 6 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.
Last scanned Nov 19, 2026, version 2.0.1.
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.
7 tools
Changes things 1Claude Code: ask
verify_retailer_authorizationCheck whether a shop is an authorized retailer of a brand, from the shop's domain or URL plus the brand or one of its products' GTIN (EAN).1 finding
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.
Findings
- Info
The description is 2,081 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ith 'Tool execution failed' is a technical error and says nothing about the data."
Description, as the server wrote it Check whether a shop is an authorized retailer of a brand, from the shop's domain or URL plus the brand or one of its products' GTIN (EAN). Read-only. Use this when you know the seller's domain, e.g. from a shopping or UCP catalog result. Pass exactly one of 'brand' or 'gtin'; a GTIN resolves the product's brand and the check stays brand-level. status: AUTHORIZED = authorization active: the brand has confirmed this shop on authorized.by; official_shop, partnership_date and certificate_url / certificate_url_de prove it, share the certificate link when a user needs proof; 'brand' in the answer is the brand that was checked. NO_RECORD_FOR_BRAND = the shop and the brand are on authorized.by, but this brand has not confirmed this shop there (also when a GTIN belongs to several brands and not exactly one confirmed it; brand is then null). RETAILER_NOT_REGISTERED = no public shop on authorized.by at this domain. BRAND_NOT_REGISTERED = 'brand' does not identify exactly one public brand (the brand is not on authorized.by, or the value is a name shared by several brands or only part of a brand's name), or no product matches 'gtin'; before telling a user that a brand is not on authorized.by, search get_brands with the name and call again with the slug of the brand that was meant. None of these statuses means that the shop is unauthorized. Domains match exactly, never a parent domain or another subdomain (www. and m. count as the same shop); marketplace hosts such as amazon.de or ebay.de only match the exact store URL. The answer is computed live, never cached. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: Verify a retailer's authorization
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 6Show 6 read-only tools
get_brandGet the public profile of one brand (manufacturer) on authorized.by.No findings
Why it is in this group
- The name "get_brand" says "get": a word for reading.
Description, as the server wrote it Get the public profile of one brand (manufacturer) on authorized.by. Read-only. Returns categories, website, headquarters country, description and the number of authorized retailers. Use get_brands first if you only know an approximate name. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: Get brand profile
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_brand_retailersList all retailers (shops) currently authorized by a brand on authorized.by.No findings
Why it is in this group
- The name "get_brand_retailers" says "get": a word for reading.
Description, as the server wrote it List all retailers (shops) currently authorized by a brand on authorized.by. Read-only. Use this to list a brand's authorized shops; to check one shop by its domain or URL, use verify_retailer_authorization. Sorted by brand_count (the number of brands that authorize the retailer) descending, then by name. Each retailer includes shop_url, official_shop (the brand's own online shop, as opposed to an independent authorized retailer), partnership_date, tuv_certified (shop identity verified in the TÜV Saarland ShopIdent procedure), and certificate_url / certificate_url_de: links to the public authorized.by certificate page (English / German) proving this specific brand-retailer authorization. Share the certificate link when a user needs verifiable proof. Only active partnerships are returned: confirmed by both the brand and the retailer, with both profiles public and both companies approved by authorized.by. Revoked or pending partnerships are never listed. Responses are cached and refreshed when the underlying profile or partnership changes, so a revocation may take a short time to disappear. partnership_date is the date the authorization STARTED, not the date it was last verified; a partnership listed here is currently active as of the response time. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: List a brand's authorized retailers
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_brandsSearch brands (manufacturers) registered on authorized.by, or list them all.No findings
Why it is in this group
- The name "get_brands" says "get": a word for reading.
Description, as the server wrote it Search brands (manufacturers) registered on authorized.by, or list them all. Read-only. 'search' matches the brand name, alias or website domain (partial match). Returns for each brand: id, name, slug, logo and the number of retailers it has authorized. Omit 'search' to retrieve the full index; use 'page' and 'size' to paginate. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: Search brands
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_retailerGet the public profile of one retailer (shop) on authorized.by.No findings
Why it is in this group
- The name "get_retailer" says "get": a word for reading.
Description, as the server wrote it Get the public profile of one retailer (shop) on authorized.by. Read-only. Returns address, contact details, opening hours, categories, registration date, tuv_certified (shop identity verified in the TÜV Saarland ShopIdent procedure: an identity check, not a certification of the retailer's business), the number of brands that authorized it, and certificate_url / certificate_url_de: links to the retailer's public authorized.by certificate page (English / German) listing all brands that authorized it. These links are null when the retailer has no active authorization. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: Get retailer profile
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_retailer_brandsList all brands a retailer (shop) is currently authorized to sell, according to authorized.by.No findings
Why it is in this group
- The name "get_retailer_brands" says "get": a word for reading.
Description, as the server wrote it List all brands a retailer (shop) is currently authorized to sell, according to authorized.by. Read-only. Use this to answer 'which brands has shop X been authorized for?'. Sorted by brand name. Each entry includes official_shop, partnership_date, and certificate_url / certificate_url_de: links to the public authorized.by certificate page (English / German) proving this specific brand-retailer authorization. Share the certificate link when a user needs verifiable proof. Only active partnerships are returned: confirmed by both the brand and the retailer, with both profiles public and both companies approved by authorized.by. Revoked or pending partnerships are never listed. Responses are cached and refreshed when the underlying profile or partnership changes, so a revocation may take a short time to disappear. partnership_date is the date the authorization STARTED, not the date it was last verified; a partnership listed here is currently active as of the response time. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: List a retailer's authorized brands
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_retailersSearch retailers (shops) registered on authorized.by, or list them all.No findings
Why it is in this group
- The name "get_retailers" says "get": a word for reading.
Description, as the server wrote it Search retailers (shops) registered on authorized.by, or list them all. Read-only. 'search' matches the company name, alias or shop domain (partial match): a URL is reduced to its domain, except on marketplace hosts such as amazon.de or ebay.de, where the store path is kept and the bare host lists every seller. A partial match can find other shops (shop.de also finds myshop.de), so compare shop_url with the domain you are checking; to verify one shop against a brand, use verify_retailer_authorization. Returns for each retailer: id, name, slug, shop URL, logo, the number of brands that authorized it, and certificate_url / certificate_url_de: links to the retailer's public authorized.by certificate page (English / German) listing all brands that authorized it; null when the retailer has no active authorization. Omit 'search' to retrieve the full index; use 'page' and 'size' to paginate. Data scope: results only cover relationships registered and confirmed on authorized.by. An empty result or a not-found error does NOT prove that no authorization exists outside authorized.by. Distinguish outcomes: an empty list means no matching record on authorized.by; an error result whose text starts with 'Brand not found' or 'Retailer not found' means the given id/alias is unknown; an error result whose text starts with 'Tool execution failed' is a technical error and says nothing about the data.
Annotations the server declares
- title: Search retailers
- 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 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, 18:31 UTC, unchanged since Oct 29, 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
- 1
- 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 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.authorized.by/api/public/mcp: tools/list returned 7 tools to an anonymous client, including verify_retailer_authorization (write)
Posture changes
- Oct 29, 2026
- Tools that change things, listed without credentials: 0 to 1
Findings
Matches of fixed checks, with the text they matched.
The description is 2,081 characters long, over the 2,000 this check looks for.
What this check looks forMatched text
description ends: "...ith 'Tool execution failed' is a technical error and says nothing about the data."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 changed.~1 changedView diff
- Changed:verify_retailer_authorizationChanges thingsdescriptioninputSchema
Tools7 changed.~7 changedView diff
- Changed:get_brandOnly readsdescriptionannotations
- Changed:get_brand_retailersOnly readsdescriptionannotations
- Changed:get_brandsOnly readsinputSchemaannotations
- Changed:get_retailerOnly readsdescriptionannotations
- Changed:get_retailer_brandsOnly readsdescriptionannotations
- Changed:get_retailersOnly readsdescriptioninputSchemaannotations
- Changed:verify_retailer_authorizationChanges thingsannotations
PostureRemote posture changed. Tools that change things, listed without credentials: 0 -> 1.View diff
- Tools that change things, listed without credentials: 0 to 1
Tools2 changed.~2 changedView diff
- Changed:get_brandsOnly readsdescriptioninputSchema
- Changed:get_retailersOnly readsdescriptioninputSchema
Tools1 added, 6 changed.+1 added~6 changedView diff
- Added:verify_retailer_authorizationChanges things
- Changed:get_brandOnly readstitleannotations
- Changed:get_brand_retailersOnly readstitledescriptionannotations
- Changed:get_brandsOnly readstitleannotations
- Changed:get_retailerOnly readstitleannotations
- Changed:get_retailer_brandsOnly readstitleannotations
- Changed:get_retailersOnly readstitleannotations
Install
Pinned to version 2.0.1. Values in angle brackets are yours to fill in.
claude mcp add --transport http brands https://app.authorized.by/api/public/mcpclaude mcp add --transport http brands https://app.authorized.by/api/public/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": [
"mcp__brands__get_brands",
"mcp__brands__get_brand",
"mcp__brands__get_brand_retailers",
"mcp__brands__get_retailers",
"mcp__brands__get_retailer",
"mcp__brands__get_retailer_brands"
],
"ask": [
"mcp__brands__verify_retailer_authorization"
],
"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 brands. 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/by.authorized/brands/verify?hash=1fbed83e22b423efde888112802c9575e03848b4a402363658e067b74900d878" | jq -e '.changed == false'Pinned hash 1fbed83e22b4, from Nov 19, 2026, 17:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/by.authorized/brands/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/by.authorized/brands)Source: MCP Registry. Synced Nov 19, 2026, 17:17 UTC.
brands MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the brands MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 1 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 brands MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the brands 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 brands MCP server have?
- 7 tools: 1 write, 6 read. verify_retailer_authorization, get_brands, get_brand, get_brand_retailers, get_retailers, get_retailer and get_retailer_brands.
Does the brands MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the brands MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the brands MCP server changed its tools?
- Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 19, 2026. Every change is on this page and in its Atom feed.