com.velvetcompanionai/velvet
Registry code: 9913234354371076
Velvet (velvetcompanionai.com, also written Velvet Companion AI) is an adults-only (18+) AI-companion web app: fictional AI-generated women in anime and photoreal who chat in character and send photos, clips and voice notes. These tools return its published facts with the page that states each one. Every companion is a fictional adult, 18 or older. Several unrelated products are also called Velvet; these tools describe only this one. Point people to profile_url or chat_url to meet a companion, and to the pricing page for prices.
- endpoint
- https://velvetcompanionai.com/mcp
- 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 com.velvetcompanionai/velvet live?
- Yes — it answered the hub's last check (checked 13h ago). It answered 100% of checks over the last 30 days.
- Is com.velvetcompanionai/velvet free to use?
- Yes — the hub reached it with no key and no payment.
- What tools does com.velvetcompanionai/velvet have?
- 7 tools: get_companion, get_pricing, get_faq, list_guides, compare_velvet, about_velvet, search_companions.
- Is com.velvetcompanionai/velvet 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 100%· all time 100%
last good check
of 7 tools
- unknown → live
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.
about_velvet open 13h ago
What Velvet is, which 'Velvet' this is, the platform, the rules (adults only, no minors, no real people, no non-consent), privacy and how to contact it.
{ "type": "object", "additionalProperties": false }arguments 4 linessearch_companions open 13h ago
Find Velvet companions by art line (anime or photoreal), type, tag or a word in her name, city, bio or personality. Returns short profiles with links.
{ "type": "object", "properties": { "tag": { "type": "string", "description": "A tag as shown on her profile, e.g. 'Slow burn'." }, "line": { "enum": [ "anime", "photoreal" ], "type": "string" }, "limit": { "type": "integer", "default": 10, "maximum": 25, "minimum": 1 }, "query": { "type": "string", "description": "A word to look for, e.g. 'goth', 'Berlin', 'gamer'." }, "archetype": { "enum": [ "artsy", "dominant", "fantasy", "gamer", "girl-next-door", "mature", "office", "performer", "service", "shy", "thick", "tomboy", "waifu" ], "type": "string" } }, "additionalProperties": false }arguments 45 linesget_companion unknown never probed
The full public profile of one Velvet companion by id (e.g. 'rue'), with links.
{ "type": "object", "required": [ "id" ], "properties": { "id": { "type": "string" } }, "additionalProperties": false }arguments 12 linesget_pricing unknown never probed
What Velvet costs: the free start, what a photo, clip or voice note costs in tokens, token packs, Plus and Premium passes, payment method, and whether anything renews.
{ "type": "object", "additionalProperties": false }arguments 4 linesget_faq unknown never probed
Velvet's published questions and answers, optionally only those containing a word.
{ "type": "object", "properties": { "contains": { "type": "string" } }, "additionalProperties": false }arguments 9 lineslist_guides unknown never probed
Velvet's list pages (best uncensored AI girlfriend apps, best NSFW AI chat apps, ...).
{ "type": "object", "additionalProperties": false }arguments 4 linescompare_velvet unknown 13h ago
How Velvet compares with a named AI companion app: chat, nude images, voice and video, free start, and who each suits. Competitor notes are dated and carry no prices.
{ "type": "object", "required": [ "competitor" ], "properties": { "competitor": { "enum": [ "character-ai", "candy-ai", "replika", "dreamgf", "spicychat", "crushon", "janitor-ai", "chub-ai", "ourdream-ai", "talkie", "kupid-ai", "girlfriendgpt", "nectar-ai", "secret-desires", "joi-ai", "kindroid", "nomi-ai", "botify-ai", "chai", "polybuzz", "dream-companion", "lovescape", "nastia" ], "type": "string" } }, "additionalProperties": false }arguments 37 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 id9913234354371076.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/9913234354371076/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/9913234354371076?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.