DataWorth AI MCP

A read-only MCP server that allows AI assistants to search a directory of AI data buyers, retrieve specific buyer eligibility rules, and check if a company fits those programs based on published criteria. It provides tools to list situations, get buyer details, and check fit without requiring user sign-in or storing personal data.

Visit DataWorth AI

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

Vendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by DataWorth AI

MCP endpoint (Streamable HTTP)

https://dataworthai.com/mcp

Vendor documentation

What you can do with it

Search for AI data buyers by industry or region
Check if a company fits specific buyer eligibility rules
Retrieve detailed buyer entries and published rules
View directory changelog updates

Source and maintenance

Vendor evidenceRegistry 1.0.0

mcp-registry: com.dataworthai/buyer-directory@1.0.0 Project website

Protocol and capabilities

Server: dataworth-ai-buyer-directory 1.2.1
MCP protocol: 2025-06-18
Tools: 5 advertised
Resources: 34 advertised
Resource templates: 1 advertised
Prompts: 1 advertised

Server-advertised capabilities

{
  "tools": {
    "listChanged": true
  },
  "prompts": {
    "listChanged": true
  },
  "resources": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

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 or predictions of what a company will receive. check_fit compares a company's basic facts with the published eligibility rules of every directory buyer that publishes clear rules, paid or not, ordered by fit and then alphabetically. Each row has its rule sources, a fee flag and its own next step (DataWorth AI's quiz for programs it works with, the buyer's own page for the rest). Results also include a disclaimer and a fee disclosure; these are part of the answer. Mode (BizBuyData) is listed by name and link only; check_fit quotes Mode's own published wording. Read-only. Stores no personal data; counts tool calls per tool per day only.

Tools

5 advertised

search_buyers — Search AI data buyers

Advertised by the server during the last successful anonymous check.

Advertised read-only

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. Use this to list or compare buyers; to compare one company's facts with programs' eligibility rules, use check_fit.

search_buyers input schema

{
  "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'."
    },
    "detail": {
      "enum": [
        "full",
        "summary"
      ],
      "type": "string",
      "description": "full (default) = every field with quotes and sources; summary = id, name, type, where, size rule and page only (smaller response; use get_buyer for one entry's full detail)."
    },
    "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."
    }
  }
}

search_buyers annotations

{
  "title": "Search AI data buyers",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

get_buyer — Get one buyer

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

get_buyer input schema

{
  "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."
    }
  }
}

get_buyer annotations

{
  "title": "Get one buyer",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

list_situations — List buyer situations

Advertised by the server during the last successful anonymous check.

Advertised read-only

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.

list_situations input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

list_situations annotations

{
  "title": "List buyer situations",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

check_fit — Check which buyers a company fits

Advertised by the server during the last successful anonymous check.

Advertised read-only

Use when someone asks whether a specific company qualifies to license its records to AI data buyers. Compares the company's industry, size, years, country, status and number of business systems with the published eligibility rules of every buyer in DataWorth AI's directory that publishes clear rules (programs DataWorth AI works with and buyers it has no relationship with alike, using the same rules as DataWorth AI's quiz for the former). Returns one row per buyer, ordered by fit and then alphabetically: meets / does not meet / needs more info, reasons quoted from that buyer's own wording, its rule source URLs, whether DataWorth AI may earn a referral fee, and its next step (the buyer's own page, or DataWorth AI's quiz for programs it introduces). Also returns a disclaimer and a fee disclosure. Returns no amounts and is not an offer. Needs no names, emails or confidential data.

check_fit input schema

{
  "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')."
    }
  }
}

check_fit output schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "summary",
    "buyers_checked",
    "results",
    "quiz_notes",
    "see_also",
    "next_step",
    "disclaimer",
    "fee_disclosure",
    "rules_basis",
    "input_used"
  ],
  "properties": {
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "id",
          "name",
          "result",
          "reasons",
          "rules_checked",
          "rule_sources",
          "rules_last_verified",
          "dataworth_may_earn_referral_fee",
          "next_step"
        ],
        "properties": {
          "id": {
            "type": "string"
          },
          "name": {
            "type": "string"
          },
          "result": {
            "enum": [
              "meets_published_rules",
              "does_not_meet_published_rules",
              "needs_more_info"
            ],
            "type": "string"
          },
          "missing": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "reasons": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "next_step": {
            "type": "object",
            "required": [
              "kind",
              "url",
              "label"
            ],
            "properties": {
              "url": {
                "type": "string"
              },
              "kind": {
                "enum": [
                  "quiz",
                  "buyer_site"
                ],
                "type": "string"
              },
              "label": {
                "type": "string"
              }
            },
            "additionalProperties": false
          },
          "rule_sources": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "rules_checked": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "directory_page": {
            "type": "string"
          },
          "rules_last_verified": {
            "type": "string"
          },
          "dataworth_may_earn_referral_fee": {
            "type": "boolean"
          }
        },
        "additionalProperties": false
      }
    },
    "summary": {
      "type": "string"
    },
    "see_also": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "slug",
          "title",
          "page"
        ],
        "properties": {
          "page": {
            "type": "string"
          },
          "slug": {
            "type": "string"
          },
          "title": {
            "type": "string"
          }
        },
        "additionalProperties": false
      }
    },
    "next_step": {
      "type": "object",
      "required": [
        "url",
        "label",
        "why"
      ],
      "properties": {
        "url": {
          "type": "string"
        },
        "why": {
          "type": "string"
        },
        "label": {
          "type": "string"
        }
      },
      "additionalProperties": false
    },
    "disclaimer": {
      "type": "string"
    },
    "input_used": {
      "type": "object",
      "required": [
        "industry",
        "employees",
        "years_operating",
        "country",
        "status"
      ],
      "properties": {
        "status": {
          "type": "string"
        },
        "country": {
          "type": "string"
        },
        "industry": {
          "type": "string"
        },
        "employees": {
          "type": "number"
        },
        "systems_count": {
          "type": "number",
          "description": "absent = not given"
        },
        "years_operating": {
          "type": "number"
        },
        "peak_employees_ever": {
          "type": "number",
          "description": "absent = not given"
        }
      },
      "additionalProperties": false
    },
    "not_scored": {
      "type": "object",
      "required": [
        "buyers",
        "why"
      ],
      "properties": {
        "why": {
          "type": "string"
        },
        "buyers": {
          "type": "array",
          "items": {
            "type": "string"
          }
        }
      },
      "additionalProperties": false
    },
    "quiz_notes": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "rules_basis": {
      "type": "object",
      "required": [
        "ordering",
        "mode",
        "method"
      ],
      "properties": {
        "mode": {
          "type": "string"
        },
        "mercor": {
          "type": "string"
        },
        "method": {
          "type": "string"
        },
        "ordering": {
          "type": "string"
        }
      },
      "additionalProperties": false
    },
    "buyers_checked": {
      "type": "number"
    },
    "fee_disclosure": {
      "type": "string"
    }
  },
  "additionalProperties": false
}

check_fit annotations

{
  "title": "Check which buyers a company fits",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

get_changelog — Directory changelog

Advertised by the server during the last successful anonymous check.

Advertised read-only

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

get_changelog input schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}

get_changelog annotations

{
  "title": "Directory changelog",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

1 advertised

does_my_company_qualify — Does my company qualify to license its data?

Advertised by the server during the last successful anonymous check.

Walks through check_fit for a company and hands off to the quiz.

company_description: e.g. '12-person law firm in Texas, 8 years old'

Resources

34 advertised

buyer-directory — DataWorth AI buyer directory (JSON, CC BY 4.0)

Advertised by the server during the last successful anonymous check.

The full published dataset, same as https://dataworthai.com/data/buyers.json.

buyer-directory URI

dataworth://directory/buyers.json

MIME type: application/json

methodology — How DataWorth AI builds the directory and checks fit

Advertised by the server during the last successful anonymous check.

methodology URI

dataworth://methodology

MIME type: text/markdown

Appen Enterprise Data — One buyer entry

Advertised by the server during the last successful anonymous check.

Appen Enterprise Data URI

dataworth://buyers/appen

MIME type: application/json

Centific Enterprise Data — One buyer entry

Advertised by the server during the last successful anonymous check.

Centific Enterprise Data URI

dataworth://buyers/centific

MIME type: application/json

CodeMerchant — One buyer entry

Advertised by the server during the last successful anonymous check.

CodeMerchant URI

dataworth://buyers/codemerchant

MIME type: application/json

Collinear AI — One buyer entry

Advertised by the server during the last successful anonymous check.

Collinear AI URI

dataworth://buyers/collinear

MIME type: application/json

DataVendor — One buyer entry

Advertised by the server during the last successful anonymous check.

DataVendor URI

dataworth://buyers/datavendor

MIME type: application/json

Defined.ai Partner Program — One buyer entry

Advertised by the server during the last successful anonymous check.

Defined.ai Partner Program URI

dataworth://buyers/defined-ai

MIME type: application/json

Google Content Offer Pilot — One buyer entry

Advertised by the server during the last successful anonymous check.

Google Content Offer Pilot URI

dataworth://buyers/google-content-pilot

MIME type: application/json

Halluminate — One buyer entry

Advertised by the server during the last successful anonymous check.

Halluminate URI

dataworth://buyers/halluminate

MIME type: application/json

Handshake AI Data Partnerships — One buyer entry

Advertised by the server during the last successful anonymous check.

Handshake AI Data Partnerships URI

dataworth://buyers/handshake-ai

MIME type: application/json

HUMXN — One buyer entry

Advertised by the server during the last successful anonymous check.

HUMXN URI

dataworth://buyers/humxn

MIME type: application/json

Labelbox Prism — One buyer entry

Advertised by the server during the last successful anonymous check.

Labelbox Prism URI

dataworth://buyers/labelbox-prism

MIME type: application/json

lalalab — One buyer entry

Advertised by the server during the last successful anonymous check.

lalalab URI

dataworth://buyers/lalalab

MIME type: application/json

LH2 AI Labs — One buyer entry

Advertised by the server during the last successful anonymous check.

LH2 AI Labs URI

dataworth://buyers/lh2-ai-labs

MIME type: application/json

Lunchbreak — One buyer entry

Advertised by the server during the last successful anonymous check.

Lunchbreak URI

dataworth://buyers/lunchbreak

MIME type: application/json

Magma — One buyer entry

Advertised by the server during the last successful anonymous check.

Magma URI

dataworth://buyers/magma

MIME type: application/json

Maryah — One buyer entry

Advertised by the server during the last successful anonymous check.

Maryah URI

dataworth://buyers/maryah

MIME type: application/json

Mercor Data — One buyer entry

Advertised by the server during the last successful anonymous check.

Mercor Data URI

dataworth://buyers/mercor-data

MIME type: application/json

micro1 Enterprise Data Partnership — One buyer entry

Advertised by the server during the last successful anonymous check.

micro1 Enterprise Data Partnership URI

dataworth://buyers/micro1-enterprise

MIME type: application/json

Mode (BizBuyData) — One buyer entry

Advertised by the server during the last successful anonymous check.

Mode (BizBuyData) URI

dataworth://buyers/mode-bizbuydata

MIME type: application/json

Nyne — One buyer entry

Advertised by the server during the last successful anonymous check.

Nyne URI

dataworth://buyers/nyne

MIME type: application/json

Ooak Data — One buyer entry

Advertised by the server during the last successful anonymous check.

Ooak Data URI

dataworth://buyers/ooak

MIME type: application/json

Pangea.ai Code Licensing — One buyer entry

Advertised by the server during the last successful anonymous check.

Pangea.ai Code Licensing URI

dataworth://buyers/pangea-code

MIME type: application/json

Polyshares — One buyer entry

Advertised by the server during the last successful anonymous check.

Polyshares URI

dataworth://buyers/polyshares

MIME type: application/json

pre.dev Code Licensing — One buyer entry

Advertised by the server during the last successful anonymous check.

pre.dev Code Licensing URI

dataworth://buyers/pre-dev

MIME type: application/json

Protege — One buyer entry

Advertised by the server during the last successful anonymous check.

Protege URI

dataworth://buyers/protege

MIME type: application/json

Scale AI Data Partnerships — One buyer entry

Advertised by the server during the last successful anonymous check.

Scale AI Data Partnerships URI

dataworth://buyers/scale-ai

MIME type: application/json

Scrimdata — One buyer entry

Advertised by the server during the last successful anonymous check.

Scrimdata URI

dataworth://buyers/scrimdata

MIME type: application/json

SuperAnnotate Data Partnerships — One buyer entry

Advertised by the server during the last successful anonymous check.

SuperAnnotate Data Partnerships URI

dataworth://buyers/superannotate

MIME type: application/json

Telegraph Lab — One buyer entry

Advertised by the server during the last successful anonymous check.

Telegraph Lab URI

dataworth://buyers/telegraph-lab

MIME type: application/json

The General Data Company — One buyer entry

Advertised by the server during the last successful anonymous check.

The General Data Company URI

dataworth://buyers/general-data-co

MIME type: application/json

Troveo (business data) — One buyer entry

Advertised by the server during the last successful anonymous check.

Troveo (business data) URI

dataworth://buyers/troveo

MIME type: application/json

Turing Project Lazarus — One buyer entry

Advertised by the server during the last successful anonymous check.

Turing Project Lazarus URI

dataworth://buyers/turing-lazarus

MIME type: application/json

buyer — One buyer entry

Advertised by the server during the last successful anonymous check.

buyer URI template

dataworth://buyers/{slug}

MIME type: application/json

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks: 1 of 1 (100%)
Average latency: 2408 ms
95th percentile latency: 2408 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

Nov 1, 2026, 7:28 AM UTC · probe · passed · 2408 ms · metadata changed · 5 tool(s), 34 resource(s), 1 resource template(s), 1 prompt(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http dataworth-ai-mcp https://dataworthai.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add dataworth-ai-mcp --url https://dataworthai.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable dataworth-ai-mcp in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "dataworth-ai-mcp": {
      "url": "https://dataworthai.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).

Cline configuration

{
  "mcpServers": {
    "dataworth-ai-mcp": {
      "type": "streamableHttp",
      "url": "https://dataworthai.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start dataworth-ai-mcp and inspect its tools.

VS Code configuration

{
  "servers": {
    "dataworth-ai-mcp": {
      "type": "http",
      "url": "https://dataworthai.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http dataworth-ai-mcp https://dataworthai.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "dataworth-ai-mcp": {
      "url": "https://dataworthai.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "dataworth-ai-mcp": {
      "serverUrl": "https://dataworthai.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like DataWorth AI MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows

See all 847

Do you run DataWorth AI MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing

DataWorth AI MCP

Endpoint and access

What you can do with it

Source and maintenance

Protocol and capabilities

Server-provided instructions

Tools

Prompts

Resources

30-day availability

Maintenance history

Connect from your client

Claude Code

Codex

Cursor

Cline

VS Code

Gemini CLI

Claude Desktop

Windsurf

Let your agent find its tools

Other crm, sales, and marketing servers

Do you run DataWorth AI MCP?