makeup.land
Registry code: cbe7beea936af103
makeup.land — Israeli professional cosmetics retailer. Use this MCP server to search the product catalog (with color-distance shade matching), look up customers by phone, fetch carts and orders, and validate gift cards. Most customer-data tools require BOTH a bearer token (`Authorization: Bearer ml_...`) AND a phone identifier — the bearer authenticates the caller, the phone selects the customer. Catalog tools (`list_products`) work anonymously for tag/brand/near_hex/sort filters. See https://makeup.land/llms-full.txt for the long-form integration guide.
- endpoint
- https://makeup.land/api/v1
- door code
- 83a87092350960eb
- protocol
- JSONRPC ·0.3
- authentication
- http, apiKey
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is makeup.land live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
- Is makeup.land free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does makeup.land have?
- 7 tools: Product search and filtering, Cart add / update / clear, Gift card validate and redeem, Customer registration, Shade matching by hex, Customer lookup and wallet balance, Order history and status.
- Is makeup.land safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 99%· all time 99.2%
last good check
of 7 tools
- degraded → live
- live → degraded· HTTP 521
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- used for
- search cosmetics by shade
- look up a customer's cart and orders
- check a gift card balance
- list cosmetics brands
- takes → gives
- text, data → data
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Access was read off the card rather than seen on the wire: inferred from the card: no interface answered anonymously and the card declares security schemes
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
product_search auth-required never probed
Search via `q` (cross-lingual natural-language query — Hebrew, English, transliteration all return semantically-equivalent results), or filter via `tag` (EXACT-string match against Hebrew-stored tags), `brand`, or `sort` (price / popularity / Bayesian-shrunk rating). Returns ILS and ℳ-credit prices side-by-side for tender-aware checkout.
cart_management auth-required never probed
Manipulate a customer's persistent cart. Supports tender selection (ils vs credits), gift-personalization. Idempotency-Key is not enforced. Stock-gated; credits-tender items wallet-gated.
gift_card_redeem auth-required never probed
Validate a gift card balance (public, no auth) or redeem against an order (scope: full or giftcards). Partner-issued + internal cards unified.
register_customer auth-required never probed
Generic registration orchestrator — create or look up a customer, compute partner-config-driven tags, fire WhatsApp template and partner webhooks. Designed for inbound WA proof of phone ownership. Scope: full or register, on a token with a registration source configured.
shade_match auth-required never probed
Find products carrying a swatch close to a target hex color, ranked by color distance (redmean-weighted RGB). Supports hue_family refinement (white, black, gray, red, coral, orange, brown, nude, beige, yellow, green, blue, purple, pink) and per-customer reward projection.
customer_lookup auth-required never probed
Lookup customer by phone (E.164). Returns tags, ℳ-credit wallet balance, M Club tier, opportunity claims.
order_history auth-required never probed
List a customer's recent orders with 6-axis status (order/payment/fulfillment/delivery/return/review).
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idcbe7beea936af103.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/cbe7beea936af103/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/cbe7beea936af103?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.