Brand Design Ltd.
REMOTE · BRANDDESIGN.LTD
AI representative of a brand, web and AI-visibility agency: ask, send an enquiry, order and pay.
Available components
Last scanned (2 hours ago)
Scores higher than 69% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Design and Media
Recent critical change
Authorization (30 Sept 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (start_payment). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability58
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 3297 tokens (~274/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 −1
- Stability: pass → 0.97 functional
- 4 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “accept_offer” rewrote its description, which is the text the model reads security
- Tool “concierge” rewrote its description, which is the text the model reads security
- Tool “create_order” rewrote its description, which is the text the model reads security
- Tool “kya_challenge” rewrote its description, which is the text the model reads security
- Tool “kya_verify” rewrote its description, which is the text the model reads security
- Tool “start_payment” rewrote its description, which is the text the model reads security
- Schema quality: 242 → 274 ▼ functional
- Schema quality: excellent → good functional
- “concierge” added an optional parameter “clientId” cosmetic
- “concierge” added an optional parameter “secret” cosmetic
- “start_payment” reworded the description of “sharedPaymentToken” cosmetic
- 30 Oct 26 0
- Schema quality: good → excellent functional
- “concierge” added an optional parameter “acting_for” cosmetic
- “concierge” added an optional parameter “agent” cosmetic
- “introduce” reworded the description of “agent” cosmetic
- 28 Oct 26 0
- Tool “concierge” rewrote its description, which is the text the model reads security
- 27 Oct 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- The server changed its declared name: Brand Design Ltd. commerce → Brand Design Ltd. security
- Schema quality: 2319 → 2770 ▼ functional
- Schema quality: excellent → good functional
- Server version: 1.1.0 → 1.2.0 functional
- New tool “concierge” functional
- New tool “introduce” functional
- 17 Oct 26 +1
- Stability: 0.97 → pass security
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://branddesign.ltd/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=branddesign.ltd | CN=YE1,O=Let's Encrypt,C=US | 10 Oct 2026 | 8 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 5ed8e9fa1c671e4ed01e53fb85a02bd6078 |
| SANs: branddesign.ltd, www.branddesign.ltd | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of branddesign.ltd. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ltd. | present | 54, 4397 | 8, 8 | Verified |
| branddesign.ltd. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains; preload |
| content-security-policy | default-src 'self'; script-src 'self' 'unsafe-inline' 'wasm-unsafe-eval' https://ajax.googleapis.com https://www.googletagmanager.com https://www.googleadservices.com https://www.google.com https://pagead2.googlesyndication.com https://googleads.g.doubleclick.net https://www.google-analytics.com https://connect.facebook.net https://bzrcdn.openai.com https://*.nitrocdn.com blob: https://apis.google.com https://www.gstatic.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' data: https://fonts.gstatic.com https://*.nitrocdn.com; img-src 'self' data: blob: https://cdn.techbehemoths.com https://www.facebook.com https://www.google-analytics.com https://region1.google-analytics.com https://www.googletagmanager.com https://googleads.g.doubleclick.net https://pagead2.googlesyndication.com https://www.googleadservices.com https://www.google.com https://google.com https://www.google.bg https://stats.g.doubleclick.net https://bzr.openai.com https://*.nitrocdn.com https://cdn-ilelpfg.nitro |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://branddesign.ltd/mcp | Verified | 200 | |
| http (plaintext) | http://branddesign.ltd/mcp | HTTPS enforced | 301 | https://branddesign.ltd/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
accept_offer ~406
Accept the offer on behalf of the buyer. Needs credentials. This locks the billing identity, the offer version and the hash of the terms as they stand at this moment. A later change to the website cannot pass for what was agreed. The request must come from a verified robot. Errors: KYA_VERIFICATION_REQUIRED or KYA_REVOKED (403) without it, OFFER_CHANGED (409) if the offer or the terms changed since you read them; read order_status and use the new values. OFFER_EXPIRED (409) 30 days after the order. MANUAL_OFFER_REQUIRED (409) while a person has not priced the service yet.
| Name | Type | Req | Description |
|---|---|---|---|
| accessToken | string | yes | The accessToken returned by create_order. |
| billing | object | yes | The buyer as it will appear on the invoice and the contract. For type company, company, registration and representative are also required. For type person, leave out company, registration, vat and re… |
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| immediateStart | boolean | – | Natural persons only: true when the buyer expressly asks the work to start within the 14-day withdrawal period and acknowledges losing the right of withdrawal once the service is fully performed. |
| offerVersion | string | yes | offer.version from the order, copied exactly. |
| order | string | yes | The order id returned by create_order. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
| termsHash | string | yes | SHA-256 of the terms page in the language of the order: offer.terms.<language>.hash from the order, copied exactly. Sending it confirms that the buyer accepts those terms. |
No output schema declared.
No examples provided.
catalog ~44
Read the service catalogue: names, prices, currency and terms. No credentials needed. All amounts are integers in the minor unit; 100000 means 1000.00 EUR.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
concierge ~366
Start here: the information desk of Brand Design Ltd. Without a question: who Brand Design Ltd. is, what it does, its clients and results and who confirms them, with links to check, and the next steps. With a question: an answer about the agency, its services, prices and how to order, from verified company knowledge, in the language of the question, with sources. When your principal wants to order, it can also prepare the offer with a checkout link, beside catalog and create_order here; it never accepts an offer or pays. Questions need no credentials. An offer is prepared only for a verified robot (signed by its maker or from the published addresses of its maker), as for create_order; credentials are optional. If your principal asks to be contacted, it can pass the enquiry to the founder. Pass the returned session to continue.
| Name | Type | Req | Description |
|---|---|---|---|
| acting_for | string | – | Optional, only if your principal agrees: the person or company you act for. The team sees it with the conversation. |
| agent | string | – | Optional: your name and platform as an agent, for example "ChatGPT agent, OpenAI" or "Claude, Anthropic". The team sees it with the conversation; the answers are the same without it. |
| clientId | string | – | Optional, unless you authenticate with the Authorization header: the clientId returned by register_agent. |
| language | string | – | Language of the introduction. Answers follow the language of the question. |
| question | string | – | Your question about Brand Design Ltd. Leave it out for the introduction. |
| secret | string | – | Optional, unless you authenticate with the Authorization header: the secret returned by register_agent. |
| session | string | – | The session code from a previous answer, to continue the conversation. |
No output schema declared.
No examples provided.
create_order ~597
Place an order for a service. Needs credentials. Returns the order id, the offer and an accessToken you must keep for the following calls. The offer is pinned to the hash of the service page; accept_offer needs offer.version and offer.terms.<language>.hash from it. Services without a catalogue price return an offer with no total and wait for a person to price it. The request must come from a verified robot: signed by its maker (Web Bot Auth) or from the published addresses of its maker. Errors: KYA_VERIFICATION_REQUIRED (403) without it, MISSING_<field> when a required brief field is absent, UNEXPECTED_FIELD when the brief has a key the service does not declare.
| Name | Type | Req | Description |
|---|---|---|---|
| brief | object | yes | Required MCP argument: send an object, including {} when the selected service has no required brief fields. Direct REST may omit brief and treats that as {}; required catalog fields remain mandatory.… |
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| idempotencyKey | string | – | Your own stable key, 16-100 characters, so a repeated call does not create a second order. If omitted this MCP adapter generates a new key for each invocation; provide and reuse a key for retries. Di… |
| language | string | – | Language of the offer, the terms and the documents. This MCP adapter defaults to en; direct REST requires payload.language explicitly. |
| lines | array | – | Only for services that have catalog.services.<service>.configurator. One entry per item: item is an id from configurator.items; qty is the number of designs, or the number of pages when the item has… |
| printQuote | boolean | – | Only with lines: the buyer would like a print quote once the design work has started. Printing is not part of this order. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
| service | string | yes | Service id: one of the keys of catalog.services, as returned by the catalog tool. |
No output schema declared.
No examples provided.
introduce ~171
Introduce yourself and the person or company you act for, and pass their enquiry to Nikola Mishev, the founder of Brand Design Ltd., by e-mail. He replies to the contact you give. Use it only when your principal wants to be contacted. No credentials needed.
| Name | Type | Req | Description |
|---|---|---|---|
| agent | string | – | Your name and platform as an agent or assistant, for example "Claude, Anthropic". |
| contact | string | yes | E-mail or phone for the reply. |
| language | string | – | Preferred language for the reply. |
| need | string | yes | What they need, in their words. |
| represents | string | yes | The person or company you act for. |
| session | string | – | The concierge session code, if you talked to the concierge first. |
| website | string | – | Their website, if any. |
No output schema declared.
No examples provided.
kya_challenge ~249
Adds the owner limit: a verified DNS record on your own domain lets your owner cap the amount per order and withdraw your right to pay by removing it. The mandatory domain verification is against the domain of your maker. Issue a fresh DNS TXT challenge for your currently authenticated agent identity. Needs commerce.order for OAuth. Supply an HTTPS contact URL on a domain you control, especially on the first OAuth connection. Omitting contact reuses the current contact. This replaces the previous challenge and clears its verification. Publish the returned txtValue at dnsName, then call kya_verify. Domain control does not establish buyer identity or grant spending authority. Do not publish secrets in DNS.
| Name | Type | Req | Description |
|---|---|---|---|
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| contact | string | – | HTTPS URL on your own public domain. No IP address, credentials, custom port or URL fragment. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
No output schema declared.
No examples provided.
kya_status ~132
Read DNS domain-control verification for your currently authenticated agent. Needs commerce.read for OAuth. Returns verification status and, when present, DNS instructions and validity timestamps. This does not change the contact, challenge or verification.
| Name | Type | Req | Description |
|---|---|---|---|
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
No output schema declared.
No examples provided.
kya_verify ~172
Check the DNS TXT challenge for your currently authenticated agent and record domain-control verification. Needs commerce.order for OAuth. First call kya_challenge and publish its exact DNS TXT record. The response gives verifiedAt and validUntil; verification is currently valid for 24 hours and is read again from DNS at every create_order, accept_offer and start_payment, which all require it. It does not grant buyer payment authority.
| Name | Type | Req | Description |
|---|---|---|---|
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
No output schema declared.
No examples provided.
manifest ~28
Read the commerce manifest: protocol, endpoints, authentication scheme, payment instrument and limits. No credentials needed.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
order_status ~146
Read the current state of the order, its offer and its payments, including the invoice number once one has been issued. Needs credentials.
| Name | Type | Req | Description |
|---|---|---|---|
| accessToken | string | yes | The accessToken returned by create_order. |
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| order | string | yes | The order id returned by create_order. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
No output schema declared.
No examples provided.
register_agent ~97
Register yourself and receive a client identifier and a secret. No approval and no prior arrangement. The secret is returned once and cannot be recovered. Put them in the Authorization header as "Bearer <clientId>:<secret>" for the other tools.
| Name | Type | Req | Description |
|---|---|---|---|
| contact | string | yes | A https:// or mailto: URL at which a human can reach whoever runs you. |
| name | string | yes | Your name, 2 to 80 characters. |
No output schema declared.
No examples provided.
start_payment ~508
Start payment for a stage. Needs credentials. Without sharedPaymentToken you receive the link to our payment page (form.redirect), which you may complete yourself with a card issued to you, or hand to the person you act for; on that page the card must be in the name on the invoice (for a company: its representative or the company name) and the cardholder address must be in the invoice country, and every order placed by an AI agent needs the cardholder to confirm with the bank (3-D Secure). With a delegated shared payment token the payment settles directly. The request must come from a verified robot: signed by its maker (Web Bot Auth) or from the published addresses of its maker. If the owner of the agent verified a DNS record with kya_challenge and kya_verify, the record is read again at payment and its limit applies; kya_status reads it. KYA does not grant buyer payment authority. On-chain payment is not accepted. Errors: OFFER_EXPIRED (409) for an advance after 30 days, FINAL_NOT_RELEASED (409) when the final payment is not open yet, OWNER_APPROVAL_REQUIRED (409) for a first order above EUR 1000 from a new e-mail or card until the merchant approves it, BUYER_BLOCKED (403), PAYMENTS_DISABLED (503).
| Name | Type | Req | Description |
|---|---|---|---|
| accessToken | string | yes | The accessToken returned by create_order. |
| clientId | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The clientId returned by register_agent. |
| order | string | yes | The order id returned by create_order. |
| secret | string | – | Required unless you authenticate with the Authorization header (Bearer <clientId>:<secret>, or an OAuth access token issued for this server). The secret returned by register_agent. |
| sharedPaymentToken | string | – | Only for delegated payment without a hosted page: a Stripe shared payment token granted to the seller profile in manifest.payment.networkBusinessProfile. Leave it out to receive the link to our payme… |
| stage | string | – | advance: the first payment, open after accept_offer. It is 50% of the total, or the whole total when the service is paid at once (paymentPlan single in the catalogue). final: the remaining 50%, open… |
No output schema declared.
No examples provided.
How do I install the Brand Design Ltd. MCP server?
Brand Design Ltd. is a hosted endpoint at https://branddesign.ltd/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · branddesign.ltd
claude mcp add --transport http ltd-branddesign-commerce 'https://branddesign.ltd/mcp'
What is the Brand Design Ltd. MCP server?
Brand Design Ltd. is an MCP server listed in the public MCP registry as ltd.branddesign/commerce. AI representative of a brand, web and AI-visibility agency: ask, send an enquiry, order and pay. This page covers its hosted endpoint (https://branddesign.ltd/mcp).
Is the Brand Design Ltd. MCP server safe to use?
Brand Design Ltd. scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Brand Design Ltd. MCP server expose?
Brand Design Ltd. exposes 12 tools: concierge, introduce, catalog, manifest, register_agent, and 7 more. Their descriptions and schemas cost roughly 2,916 tokens of context every time the server is loaded.
Does the Brand Design Ltd. MCP server require authentication?
No. We connected to Brand Design Ltd. without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Brand Design Ltd. MCP server still maintained?
Brand Design Ltd. is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.