FounderBrain
See how a founder came across in a pitch or investor call, compared with 773 founder interviews.
Should I use this
Quality & Safety
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"founderbrain": {
"url": "https://mcp.thinkreasonlearn.com/mcp"
}
}
}Remote endpoints
https://mcp.thinkreasonlearn.com/mcpstreamable-httpWhat it can do
Tool inventory
Tools (3)
🟢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.
Input Schema
{
"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"
}Output Schema
{
"type": "object",
"properties": {
"person": {
"type": "string",
"description": "The speaker as named in the report."
},
"note": {
"type": [
"string",
"null"
],
"description": "A note on reading the report, such as for a speaker who mostly asked questions."
},
"archetype": {
"type": "object",
"description": "The speaking type: name, sketch, description and best-known members."
},
"headline": {
"type": "string",
"description": "One line on where the speaker differs most from the reference interviews."
},
"styles": {
"type": "array",
"items": {
"type": "object"
},
"description": "Positions on four speaking styles, as percentiles against the reference interviews."
},
"closest_match": {
"type": "object",
"description": "The well-known founder or operator whose style is closest."
},
"similar_people": {
"type": "array",
"items": {
"type": "object"
},
"description": "Other well-known people with a similar style, with match percentages."
},
"least_like_you": {
"type": "object",
"description": "The well-known person whose style is least alike."
},
"standout_habits": {
"type": "array",
"items": {
"type": "object"
},
"description": "Habits whose rate differs most from the reference interviews."
},
"takeaways": {
"type": "array",
"items": {
"type": "object"
},
"description": "What to try next time and what to keep."
},
"coverage": {
"type": "object",
"description": "How much of the transcript was analysed, and whether the result is settled."
},
"method": {
"type": "string"
},
"how_to_read": {
"type": "object"
},
"words_received": {
"type": "integer",
"description": "Words in the transcript received."
},
"speaker": {
"type": "string",
"description": "The speaker label analysed, as it appears in the transcript."
},
"role": {
"type": "string",
"enum": [
"answering",
"asking"
]
},
"how_to_use": {
"type": "string",
"description": "How the assistant should coach from these results."
}
},
"required": [
"person",
"archetype",
"headline",
"styles",
"closest_match",
"takeaways",
"coverage",
"words_received",
"speaker",
"role"
],
"additionalProperties": true
}🟢open_in_terminal(path, speaker, name, role)
Returns a curl command that uploads a local transcript file (.docx, .txt, .md or .vtt) to FounderBrain for analysis, for clients that run commands on the user's own computer, such as Claude Code and Codex. path: the file's full local path. speaker, name and role: the speaker label to analyse, the person's name when the label is generic, and "answering" or "asking". Without a speaker the command only lists the speakers and their word counts.
Input Schema
{
"type": "object",
"properties": {
"path": {
"title": "Path",
"type": "string"
},
"speaker": {
"default": "",
"title": "Speaker",
"type": "string"
},
"name": {
"default": "",
"title": "Name",
"type": "string"
},
"role": {
"default": "answering",
"title": "Role",
"type": "string"
}
},
"required": [
"path"
],
"title": "open_in_terminalArguments"
}Output Schema
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "open_in_terminalOutput"
}🟢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").
Input Schema
{
"type": "object",
"properties": {
"transcript": {
"default": "",
"title": "Transcript",
"type": "string"
}
},
"title": "check_transcriptArguments"
}Output Schema
{
"type": "object",
"additionalProperties": true,
"title": "check_transcriptDictOutput"
}Community
Evidence