Dataconto: who buys company records and code
Who pays owners for company records, code and datasets, closed companies included. Sourced terms.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"buyers": {
"url": "https://dataconto.com/mcp"
}
}
}遠端端點
https://dataconto.com/mcpstreamable-http它能做什麼
工具清單
工具(4)
🟢list_buyers(side, kind, status, country, min_payout, ...)
Programs that pay owners for company records (email, chat, tickets, docs, CRM, databases) or private code, including from closed or winding-down companies. Returns each program's summary, who qualifies, published payout range or rates, countries and its Dataconto page. Programs listed on Dataconto's buyer pages come first.
輸入結構描述
{
"type": "object",
"properties": {
"side": {
"type": "string",
"enum": [
"company",
"code"
],
"description": "company = business records, code = private source code."
},
"kind": {
"type": "string",
"enum": [
"pays_owner",
"marketplace",
"invite_only"
],
"description": "pays_owner = the program pays the owner itself; marketplace = it places the data with buyers; invite_only = no open intake."
},
"status": {
"type": "string",
"enum": [
"open",
"invite",
"paused",
"closed"
],
"description": "Intake status."
},
"country": {
"type": "string",
"description": "Two-letter ISO 3166 code of the owner's country, e.g. US, GB, DE. Programs with no country limit are included."
},
"min_payout": {
"type": "integer",
"minimum": 0,
"description": "Only programs whose published payout reaches at least this many US dollars."
},
"listed": {
"type": "boolean",
"description": "true = only programs on Dataconto's buyer pages and fit check."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Results to return, default 20."
}
},
"additionalProperties": false
}🟢get_buyer(id)
One program with its current facts: what it takes, who qualifies, payout, fees, exclusivity, payment timing and process, each quoted from the buyer's page with the date read.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Program id from list_buyers, e.g. \"scale-data-partnerships\". A company name also works."
}
},
"required": [
"id"
],
"additionalProperties": false
}🟢get_market_facts(program, field, source_type, since, current, ...)
Dated, sourced facts across programs: payout ranges, per-token rates, payout caps, platform fees, payment timing, eligibility. History is kept when a term changes (current=false rows). Press-only figures are flagged with source_type press.
輸入結構描述
{
"type": "object",
"properties": {
"program": {
"type": "string",
"description": "Program id from list_buyers."
},
"field": {
"type": "string",
"enum": [
"payout_range",
"payout_rate",
"payout_cap",
"payout_total",
"platform_fee",
"payment_timing",
"exclusivity",
"eligibility",
"buys",
"process",
"deal",
"ownership"
],
"description": "Kind of fact."
},
"source_type": {
"type": "string",
"enum": [
"primary",
"press",
"register"
],
"description": "primary = quoted from the buyer's own page."
},
"since": {
"type": "string",
"description": "Observed on or after this date, YYYY-MM-DD."
},
"current": {
"type": "boolean",
"description": "true = only terms in force; false = only superseded ones."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Results to return, default 30."
}
},
"additionalProperties": false
}🟢get_tool_terms(tool, record_type, field, plan, answer, ...)
For business tools companies keep records in (chat, email, tickets, docs, CRM, call recordings, code hosts): who owns the customer's data, whether the vendor trains AI on it (generative and other models, by plan), whether it keeps aggregated use, what can be exported on which plan and by whom, how much history the plan keeps, and how long data stays after cancellation. Each answer is quoted word for word from the vendor's own terms, AI page, data processing addendum or help article, with the date read. "The terms don't say" means every contract was read and none answers; "Not read yet" means a document is still unread. Answers marked inferred are a reading of the text, not its words. Not legal advice.
輸入結構描述
{
"type": "object",
"properties": {
"tool": {
"type": "string",
"description": "Tool id, e.g. \"slack\", \"microsoft-365\", \"google-workspace\", \"salesforce\", \"notion\". Omit to list every tool."
},
"record_type": {
"type": "string",
"description": "Kind of record: slack-and-teams, email, support-tickets, jira-and-linear, crm, call-recordings, documents-and-sops."
},
"field": {
"type": "string",
"enum": [
"ownership",
"ai_training",
"aggregate_use",
"export",
"retention",
"after_cancel"
],
"description": "One question: ownership, ai_training, aggregate_use, export, retention or after_cancel."
},
"plan": {
"type": "string",
"description": "A plan name as the vendor spells it, e.g. \"Free\", \"Enterprise\"."
},
"answer": {
"type": "string",
"enum": [
"customer",
"vendor",
"shared",
"not_stated",
"no",
"opt_in",
"opt_out",
"yes",
"reserved",
"not_reserved",
"all",
"partial",
"none",
"days",
"export",
"no_export"
],
"description": "Keep tools whose headline answer has this token, e.g. opt_out with field=ai_training."
},
"facts": {
"type": "boolean",
"description": "false = headline answers only, no quoted facts. Default true."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"description": "Tools to return, default 20."
}
},
"additionalProperties": false
}社群
證據