FounderBrain

See how a founder came across in a pitch or investor call, compared with 773 founder interviews.

我該用這個嗎

品質與安全性

B
說明品質
90%
結構描述完整度
68%
命名品質
90%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~452Token(工具定義)
~831 B典型回應大小
極小的注意力影響(128k 上下文的 0.35%)

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": {
    "founderbrain": {
      "url": "https://mcp.thinkreasonlearn.com/mcp"
    }
  }
}

遠端端點

https://mcp.thinkreasonlearn.com/mcpstreamable-http

它能做什麼

工具清單

工具(2)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢analyse_transcript(transcript, speaker, name, role)

Compare one speaker in a meeting transcript with public founder and operator interviews and return the report as data: speaking type, style positions, similar well-known people, standout habits and takeaways. transcript: the whole text, one speaker turn per line ("Name: words"). speaker: one speaker label as it appears in the text. name: the person's name when the label is generic (Me, Them, Speaker 2), or "You" when the speaker is the user; required for a generic label other than Me. role: "answering" when they were pitching or answering questions, "asking" when they mostly asked them. Needs at least 300 words from the speaker and at most 15,000 words in all; usually takes under a minute, up to about two minutes when the service is starting up. Clients that support MCP Apps also show the visual report.

輸入結構描述

{
  "type": "object",
  "properties": {
    "transcript": {
      "default": "",
      "title": "Transcript",
      "type": "string"
    },
    "speaker": {
      "default": "",
      "title": "Speaker",
      "type": "string"
    },
    "name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Name"
    },
    "role": {
      "default": "answering",
      "title": "Role",
      "type": "string"
    }
  },
  "title": "analyse_transcriptArguments"
}
🟢check_transcript(transcript)

List the speakers in a meeting transcript and how many words each said, without scoring anything. transcript: the whole text, one speaker turn per line ("Name: words").

輸入結構描述

{
  "type": "object",
  "properties": {
    "transcript": {
      "default": "",
      "title": "Transcript",
      "type": "string"
    }
  },
  "title": "check_transcriptArguments"
}

輸出結構描述

{
  "type": "object",
  "additionalProperties": true,
  "title": "check_transcriptDictOutput"
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本2 個工具