Clair is an MCP server published by co.meetclair, hosted at www.meetclair.co. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including get_signup_schema, join_waitlist, update_waitlist.
Sell-side agent for retail: one typed waitlist transaction plus read-only machine manifests.
37 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Returns the authoritative JSON schema, required fields and privacy terms for the waitlist transaction (exactly what GET /api/signup returns). Read this before joining.
No parameters.
{
"name": "get_signup_schema",
"title": "Get the signup schema",
"description": "Returns the authoritative JSON schema, required fields and privacy terms for the waitlist transaction (exactly what GET /api/signup returns). Read this before joining.",
"inputSchema": {
"type": "object",
"properties": {}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
One typed transaction: joins the named person to the Clair pilot waitlist. consent: true is a recorded claim - assert it only with the person's consent. One submission per person; repeats return already: true. Returns an edit_token binding follow-up details. Identify yourself with agent_name, agent_operator, on_behalf_of.
| Parameter | Type | Description |
|---|---|---|
| email * | string | Email of the person joining. |
| consent * | boolean | Must be true. Recorded claim of the named person's consent. |
| agent_name | string | Optional self-identification: your name as an agent. |
| on_behalf_of | string | Optional self-identification: who sent you. |
| agent_operator | string | Optional self-identification: who operates you. |
{
"name": "join_waitlist",
"title": "Join the Clair pilot waitlist",
"description": "One typed transaction: joins the named person to the Clair pilot waitlist. consent: true is a recorded claim - assert it only with the person's consent. One submission per person; repeats return already: true. Returns an edit_token binding follow-up details. Identify yourself with agent_name, agent_operator, on_behalf_of.",
"inputSchema": {
"type": "object",
"required": [
"email",
"consent"
],
"properties": {
"email": {
"type": "string",
"description": "Email of the person joining."
},
"consent": {
"type": "boolean",
"description": "Must be true. Recorded claim of the named person's consent."
},
"agent_name": {
"type": "string",
"description": "Optional self-identification: your name as an agent."
},
"on_behalf_of": {
"type": "string",
"description": "Optional self-identification: who sent you."
},
"agent_operator": {
"type": "string",
"description": "Optional self-identification: who operates you."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Merges follow-up details into an existing waitlist record. Requires the edit_token returned by join_waitlist - email alone never authorizes a merge. A repeat with nothing new returns already: true. All detail fields optional: name, company, role, context (one line: what they sell), why (the problem they are solving), question (anything they want to ask).
| Parameter | Type | Description |
|---|---|---|
| why | string | What brought them here - the problem to solve. |
| name | string | |
| role | string | |
| email * | string | The email used at join time. |
| company | string | |
| consent * | boolean | Must be true. |
| context | string | One line: what they sell. |
| question | string | Anything they want to ask Clair. |
| edit_token * | string | Token returned by join_waitlist. |
{
"name": "update_waitlist",
"title": "Add details to a waitlist record",
"description": "Merges follow-up details into an existing waitlist record. Requires the edit_token returned by join_waitlist - email alone never authorizes a merge. A repeat with nothing new returns already: true. All detail fields optional: name, company, role, context (one line: what they sell), why (the problem they are solving), question (anything they want to ask).",
"inputSchema": {
"type": "object",
"required": [
"email",
"consent",
"edit_token"
],
"properties": {
"why": {
"type": "string",
"description": "What brought them here - the problem to solve."
},
"name": {
"type": "string"
},
"role": {
"type": "string"
},
"email": {
"type": "string",
"description": "The email used at join time."
},
"company": {
"type": "string"
},
"consent": {
"type": "boolean",
"description": "Must be true."
},
"context": {
"type": "string",
"description": "One line: what they sell."
},
"question": {
"type": "string",
"description": "Anything they want to ask Clair."
},
"edit_token": {
"type": "string",
"description": "Token returned by join_waitlist."
}
}
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Clair is the sell-side agent retailers deploy to welcome buy-side agents. This deployment runs one small typed transaction: joining the Clair pilot waitlist. Call get_signup_schema first - it is authoritative. Then join_waitlist with email and consent: true (a recorded claim - assert it only with the person's consent). The response edit_token binds follow-ups: update_waitlist merges new details into the same record. Identify yourself with agent_name, agent_operator and on_behalf_of - declared agents are welcome; classification never blocks.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.