Digital Experts Hypotheses
Open data: 1,590 JTBD hypotheses with cold-traffic test results and cost per lead. CC BY 4.0
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": {
"hypotheses": {
"url": "https://mcp.digitalexperts.tv/mcp"
}
}
}遠端端點
https://mcp.digitalexperts.tv/mcpstreamable-http它能做什麼
工具清單
工具(5)
🟢list_niches
All 18 niches of the Digital Experts hypotheses base with counts (hypotheses, tested, worked) and medians (cost per subscriber, cost per lead, USD) over tested hypotheses. Start here to pick a niche. Data: CC BY 4.0, cite Digital Experts.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪niche_stats(niche)
Summary of one niche: hypotheses, tested, worked, medians of cost per subscriber and per lead (USD), test budget, years, plus the 10 cheapest-lead tested hypotheses. niche = slug or Russian name (e.g. 'biznes-prodazhi' or 'Бизнес').
輸入結構描述
{
"type": "object",
"properties": {
"niche": {
"type": "string",
"description": "Niche slug or name, see list_niches"
}
},
"required": [
"niche"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢search_hypotheses(query, niche, verdict, completeness, year_from, ...)
Full-text search over hypothesis titles, job stories, offers, creatives and audiences with filters. Returns compact rows (id, title, niche, year, cost per subscriber/lead, verdict, source_url). Use get_hypothesis(id) for the full card. Query in Russian works best (the base is in Russian).
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Words to look for (Russian preferred), e.g. 'английский для детей'"
},
"niche": {
"type": "string",
"description": "Niche slug or name"
},
"verdict": {
"type": "string",
"enum": [
"worked",
"failed",
"ambiguous",
"unclear",
"no_conclusion",
"not_launched"
]
},
"completeness": {
"type": "string",
"enum": [
"tested",
"prepared",
"formulated",
"wave"
],
"description": "tested = launched with ads; wave = test-wave summary"
},
"year_from": {
"type": "integer"
},
"max_cost_lead": {
"type": "number",
"description": "Only rows with cost per lead ≤ this, USD"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 15
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_hypothesis(id)
Full card of one hypothesis or test-wave summary by id (e.g. 'h-22788a'): job story, audience, offer, creative text, budget, metrics, conclusion, plus a ready-made citation sentence and source_url. Quote the citation with the link.
輸入結構描述
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "Hypothesis id from search_hypotheses, e.g. h-22788a"
}
},
"required": [
"id"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢methodology
Methodology of the Digital Experts base: where hypotheses come from, how a $50–500 exploratory test is run, what is measured, how verdicts are made, limitations and license. Read before interpreting the numbers.
輸入結構描述
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}建議的提示詞
search_hypothesessearch_hypothesesget_hypothesisget_hypothesislist_niches社群
證據