_ registry / mcp streamable-http · checked 43m ago

dataworth-ai-buyer-directory

https://dataworthai.com

Registry code: fa36c2deeb62b866

api record

DataWorth AI's buyer directory lists companies and programs that license a business's operating records (email, chat, files, CRM, code, CAD) to AI developers.

Every fact comes from that company's own website on the date in last_verified. null means not published. Payouts are quoted in the company's own words and are not offers; never present them as what a company will get.

endpoint
https://dataworthai.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 it live, free and safe measured by this hub
Is dataworth-ai-buyer-directory live?
Yes — it answered the hub's last check (checked 43m ago). It answered 100% of checks over the last 30 days.
Is dataworth-ai-buyer-directory free to use?
Yes — the hub reached it with no key and no payment.
What tools does dataworth-ai-buyer-directory have?
5 tools: get_buyer, check_fit, search_buyers, get_changelog, list_situations.
Is dataworth-ai-buyer-directory 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.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
853ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1 checks · signed record
  • unknown → live
_ usage and payments 30 days

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.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
2 open 3 never probed 2 of 5 classified

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.

  • get_changelog open 43m ago

    What changed in the buyer directory and when (newest first), plus what was left out and why.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
    arguments 5 lines
  • list_situations open 43m ago

    The directory's situation lists (closed or winding-down companies, under 30 employees, outside the US, source code, engineering/CAD, professional services) with the buyers in each and the page link.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
    arguments 5 lines
  • get_buyer unknown never probed

    Full directory entry for one buyer or program by its id (slug), e.g. 'lunchbreak', 'micro1-enterprise', 'turing-lazarus'. Includes its own quoted rules, sources and last-verified date.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "maxLength": 80,
      "minLength": 1,
      "description": "Buyer id from search_buyers, or the last part of its dataworthai.com/buyers/<slug>/ page."
    }
  }
}
    arguments 15 lines
  • check_fit unknown 43m ago

    Compares a company's basic facts with the PUBLISHED eligibility rules of the programs DataWorth AI works with (Mode, micro1, Lunchbreak), using the same rules as DataWorth AI's quiz, with reasons quoted from each program's own wording. Returns no amounts. Not an offer. Always show the user the disclaimer, fee_disclosure and next_step link. Don't ask for names, emails or confidential data; none is needed.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "industry",
    "employees",
    "years_operating",
    "country",
    "status"
  ],
  "properties": {
    "status": {
      "enum": [
        "operating",
        "winding_down",
        "closed",
        "acquired"
      ],
      "type": "string",
      "description": "operating, winding_down, closed, or acquired."
    },
    "country": {
      "type": "string",
      "maxLength": 60,
      "minLength": 2,
      "description": "Where the company is based: US, CA, UK, AU, or any other country name (treated as OTHER)."
    },
    "systems": {
      "type": "array",
      "items": {
        "enum": [
          "email",
          "chat",
          "files",
          "crm",
          "practice",
          "billing",
          "projects",
          "tickets",
          "calls"
        ],
        "type": "string"
      },
      "maxItems": 20,
      "description": "Alternative to systems_count: which systems it uses."
    },
    "industry": {
      "enum": [
        "legal",
        "accounting",
        "finance",
        "medical",
        "dental",
        "insurance",
        "staffing",
        "title-escrow",
        "property-management",
        "real-estate-brokerage",
        "software",
        "engineering",
        "manufacturing",
        "life-sciences",
        "games",
        "other"
      ],
      "type": "string",
      "description": "legal, accounting, finance, medical, dental, insurance, staffing, title-escrow, property-management, real-estate-brokerage, software, engineering (incl. architecture/design), manufacturing (incl. machine shops), life-sciences (labs and research), games, or other."
    },
    "employees": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Employees today (full-time)."
    },
    "systems_count": {
      "type": "integer",
      "maximum": 50,
      "minimum": 0,
      "description": "How many business systems it uses (email, chat, file storage, CRM, practice/billing, projects, tickets, calls). Mode asks for 5+."
    },
    "years_operating": {
      "type": "number",
      "maximum": 300,
      "minimum": 0,
      "description": "Years the company has operated / has records for."
    },
    "peak_employees_ever": {
      "type": "integer",
      "maximum": 1000000,
      "minimum": 0,
      "description": "Most people it has ever employed (used for Lunchbreak's '20+ staff at some point')."
    }
  }
}
    arguments 94 lines
  • search_buyers unknown never probed

    Search DataWorth AI's directory of companies and programs that license a business's operating records (email, chat, files, CRM, code, CAD) to AI developers. Facts come from each company's own site; payouts are quoted in its own words and are not offers. Results are alphabetical (or by text relevance when a query is given), never by referral fee. For whether a specific company fits, use check_fit.

    mcp-tool

    {
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "Free text, e.g. 'source code', 'law firm', 'wind-down'."
    },
    "region": {
      "enum": [
        "US",
        "outside_US"
      ],
      "type": "string",
      "description": "outside_US = buyers whose pages say they take or estimate for non-US companies."
    },
    "industry": {
      "enum": [
        "legal",
        "accounting",
        "finance",
        "medical",
        "dental",
        "insurance",
        "staffing",
        "title-escrow",
        "property-management",
        "real-estate-brokerage",
        "software",
        "engineering",
        "manufacturing",
        "life-sciences",
        "games",
        "other"
      ],
      "type": "string",
      "description": "Only buyers whose own pages name this industry. Many buyers take records from any industry; omit to see them."
    },
    "data_type": {
      "enum": [
        "email",
        "chat",
        "documents",
        "crm",
        "code",
        "cad_engineering",
        "support_tickets",
        "calls",
        "finance_erp",
        "healthcare",
        "media",
        "agent_traces"
      ],
      "type": "string",
      "description": "Kind of records the buyer says it licenses."
    },
    "max_results": {
      "type": "integer",
      "maximum": 40,
      "minimum": 1,
      "description": "Default 10."
    },
    "accepts_closed": {
      "type": "boolean",
      "description": "true = only buyers whose pages say they take winding-down or closed companies."
    }
  }
}
    arguments 69 lines
_ try it through the hub, ceiling 0

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.

_ is this your agent? claim it: badge, payouts, history

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.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. 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.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id fa36c2deeb62b866.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/fa36c2deeb62b866/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/fa36c2deeb62b866/badge.svg)](https://brick.blue/agent/fa36c2deeb62b866?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.

_ how we know
card completeness
90%

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.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
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.