BPJ Startup Research
BPJ startup cases, launch signals and validation plans. Free preview; member tools use scoped keys.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"bpj-startup-research": {
"url": "https://baipiaoji.com/api/startup-mcp"
}
}
}远程端点
https://baipiaoji.com/api/startup-mcpstreamable-http它能做什么
工具清单
工具（5）
🟢startup_preview(language)
Free preview of dated business evidence and launch signals. Explains membership access, limits and caveats; no key needed.
输入模式
{
"type": "object",
"properties": {
"language": {
"type": "string",
"enum": [
"zh",
"en"
]
}
},
"required": [],
"additionalProperties": false
}🟢search_startup_cases(query, outcome, scope, category, language, ...)
MEMBER: find source-backed AI startup cases, with dated revenue/adoption/failure evidence. Default excludes company references. Relevance is not success probability.
输入模式
{
"type": "object",
"properties": {
"query": {
"type": "string",
"maxLength": 500
},
"outcome": {
"type": "string",
"enum": [
"success",
"failure",
"all"
]
},
"scope": {
"type": "string",
"enum": [
"non-company",
"solo",
"small-team",
"company",
"unknown",
"all"
]
},
"category": {
"type": "string",
"maxLength": 60
},
"language": {
"type": "string",
"enum": [
"zh",
"en"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [],
"additionalProperties": false
}🟢compare_startup_cases(ids, language)
MEMBER: compare 2–4 reviewed cases for the same customer job. Retains metric periods, team evidence and limits; never converts revenue to profit.
输入模式
{
"type": "object",
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string",
"maxLength": 80
},
"minItems": 2,
"maxItems": 4,
"uniqueItems": true
},
"language": {
"type": "string",
"enum": [
"zh",
"en"
]
}
},
"required": [
"ids"
],
"additionalProperties": false
}🟢get_startup_radar(source, focus, history, language, limit)
MEMBER: query daily Show HN discussion samples and Product Hunt launches, with dates and optional retained history. Launches and keywords are unreviewed; no revenue or solo verdict.
输入模式
{
"type": "object",
"properties": {
"source": {
"type": "string",
"enum": [
"all",
"hn",
"ph"
]
},
"focus": {
"type": "string",
"enum": [
"consumer",
"consumer-ai",
"ai",
"all"
]
},
"history": {
"type": "boolean"
},
"language": {
"type": "string",
"enum": [
"zh",
"en"
]
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 20
}
},
"required": [],
"additionalProperties": false
}🟢build_startup_plan(question, skill, customer, stage, budget, ...)
MEMBER: build a source-linked 14-day validation plan, opposing success/failure evidence, unit economics and website-upgrade suggestions. Local retrieval and neural representation, no external LLM. Do not send customer secrets.
输入模式
{
"type": "object",
"properties": {
"question": {
"type": "string",
"maxLength": 500
},
"skill": {
"type": "string",
"maxLength": 240
},
"customer": {
"type": "string",
"maxLength": 240
},
"stage": {
"type": "string",
"maxLength": 120
},
"budget": {
"type": "number",
"minimum": 0,
"maximum": 1000000000
},
"hours": {
"type": "number",
"minimum": 0,
"maximum": 168
},
"price": {
"type": "number",
"minimum": 0,
"maximum": 1000000000
},
"variableCost": {
"type": "number",
"minimum": 0,
"maximum": 1000000000
},
"fixedCost": {
"type": "number",
"minimum": 0,
"maximum": 1000000000000
},
"language": {
"type": "string",
"enum": [
"zh",
"en"
]
}
},
"required": [
"question"
],
"additionalProperties": false
}社区
证据