ynt-labs
Registry code: 534ba9e634dc35a9
This is the house MCP for ynt-labs (https://ynt.codes): a read-only
catalog of everything this operator runs, plus one tool that only
- endpoint
- https://ynt.codes/mcp
- door code
- f884958fac4994e8
- protocol
- streamable-http ·2025-06-18
- authentication
- none observed
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is ynt-labs live?
- Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.
- Is ynt-labs free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does ynt-labs have?
- 5 tools: ynt_get_product, ynt_how_to_buy, ynt_prepare_service_request, ynt_ecosystem_pulse, ynt_list_products.
- Is ynt-labs 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 99.2%· all time 99%
last good check
of 5 tools
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- live → degraded· timeout after 20000ms
- degraded → live
- used for
- get ecosystem status
- get product details
- list products
- draft service request email
- understand payment process
- takes → gives
- text, data → text, data
- tools
- 4 reads1 changes 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
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.
ynt_ecosystem_pulse reads open 9h ago
Measure the ecosystem's 5 live signals right now, in parallel, with a 3-second timeout each. Never cached: a signal that cannot be measured comes back 'unmeasured', never guessed. Each signal carries a 'kind': 'check' signals carry a boolean 'ok' (true/false) that is a real health verdict; 'info' signals (a dated fact with nothing to judge) always carry ok:null, even when status is 'measured' — never true, so a caller cannot mistake 'we read a date' for 'this is healthy'.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesynt_list_products reads open 9h ago
List the ynt-labs catalog (the same one at https://ynt.codes/ecosistema): proof, product, fleet and client entries, with their status, links and discovery surface. Optionally filtered to one trust layer.
{ "type": "object", "properties": { "layer": { "enum": [ "prueba", "producto", "flota", "clientes" ], "type": "string", "description": "Restrict the listing to one trust layer." } }, "additionalProperties": false }arguments 16 linesynt_get_product reads unknown 9h ago
Get one catalog entry by id: its status, links, discovery surface, declared tools, declared relations ('uses'), and — for nomicheck, sobre and verificador — how to actually use or verify it.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "enum": [ "ynt-labs", "sobre", "verificador", "vaultwatch", "nomicheck", "nagual", "testigo", "plebe", "grimorio", "resplandor-landing", "resplandor-pos", "salon-911", "advance-fitness" ], "type": "string", "description": "Catalog id." } }, "additionalProperties": false }arguments 28 linesynt_how_to_buy reads unknown never probed
The paid path, step by step: how to reach NomiCheck's own MCP, what is free first, how the x402 402 response works, and where to check prices. Read this before attempting any payment.
{ "type": "object", "properties": {}, "additionalProperties": false }arguments 5 linesynt_prepare_service_request changes data unknown 6h ago
Draft a service-request email (consulting, development, x402 integration, verifiable outputs, or other). Drafts only: nothing is sent and nothing is stored, and it refuses unless human_confirmed is explicitly true — a real person has to confirm before this drafts anything.
{ "type": "object", "required": [ "requester_name", "contact", "service", "description", "human_confirmed" ], "properties": { "contact": { "type": "string", "maxLength": 200, "minLength": 1, "description": "Email or another way to reach the requester." }, "service": { "enum": [ "consulting", "development", "x402-integration", "verifiable-outputs", "other" ], "type": "string" }, "timeline": { "type": "string", "maxLength": 200 }, "budget_usd": { "type": "number", "minimum": 0 }, "description": { "type": "string", "maxLength": 4000, "minLength": 20 }, "requester_name": { "type": "string", "maxLength": 200, "minLength": 1 }, "human_confirmed": { "type": "boolean", "description": "Must be true: a human has explicitly confirmed sending this." } }, "additionalProperties": false }arguments 51 lines
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 id534ba9e634dc35a9.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/534ba9e634dc35a9/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/534ba9e634dc35a9?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.
Served from the same domain, which is what was measured. Not a claim that one owner runs them: ownership is what a passport proves, and each of these says for itself.
- nomicheck.ynt.codes nomicheck
- nagual.ynt.codes nagual