LABSCO SUMMARY

It ships personas, not answers — the roleplay happens in your client.

summon_legend and get_legend_context hand back the persona and stop there; nothing in the tool list generates the reply, so what you read is your own model wearing the voice. The roster is the fixed set named in list_legends, and the framing is unmistakably proactive — suggest is written to be called on questions about business, startups, investing, crypto, AI, leadership and life advice, and returns an action for the client to execute rather than an answer to read.

What it is

A persona library: the tools return a named founder's or investor's identity, voice, principles and thinking frameworks as context, and your model answers in that character.

What you get

A fixed roster you can browse: list_legends groups it into Tech Titans (Elon Musk, Steve Jobs, Jeff Bezos, Jensen Huang), Investors (Warren Buffett, Charlie Munger, Peter Thiel, Marc Andreessen), Startup Sages (Paul Graham, Sam Altman, Naval Ravikant, Reid Hoffman) and Crypto Builders (CZ, Anatoly Yakovenko, Mert Mumtaz, Michael Heinrich).
search_legends finds them by name, description, expertise or tags — 'first principles' resolves to Elon Musk, 'investor' to Buffett, Munger and Thiel.
summon_legend returns one legend's full persona context so the reply comes back in that voice, and get_legend_context returns the long form: identity, voice and style, core principles, thinking frameworks and anti-patterns.
party_mode puts one question to several legends at once and returns each of them answering in their own voice.
auto_match reads a question, matches legends by expertise and returns them with key insights; get_legend_insight returns a single wisdom snippet on a topic; suggest returns a ready-to-execute primary_action naming the tool to call next.

Requirements

No account and no key. The tools return persona text for the model to answer with, so the quality of the reply depends on the model in your client.

Setup effort

One command — npx legends-mcp

See installation options

USE CASES

01

Getting a decision looked at in one particular person's voice

Find the legend whose expertise fits the question, load their persona, and go deeper into principles and anti-patterns when the first answer is too general.

search_legendssummon_legendget_legend_context

02

Hearing the argument from more than one side of the table

Put the question to several legends at once and let the disagreement surface, or have the relevant ones picked for you when you do not know whom to ask.

auto_matchparty_modelist_legends

03

Pulling one usable line out mid-conversation

When the conversation is already running and you want a single framing rather than a full persona, take the snippet or let the server name the action to run next.

get_legend_insightsuggest

8 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`auto_match`

Automatically find the most relevant legends for your question.

How it works:

Analyzes your question for topics and keywords
Matches relevant legends based on their expertise
Returns matched legends with key insights

Use this when:

You're not sure which legend to ask
You want to see who has expertise in your topic
You want quick insights before a full conversation

What you get:

Top 2-3 most relevant legends
Why each was matched
A key insight from each
Suggested next steps

Examples:

"How do I raise money for my startup?" → Paul Graham, Marc Andreessen
"What's the future of AI?" → Sam Altman, Jensen Huang
"How should I think about risk?" → Ray Dalio, Howard Marks

DISCLAIMER: AI personas for educational purposes only.

`suggest`

🔮 PROACTIVE LEGEND SUGGESTER - Returns ready-to-execute actions!

⚡ USE THIS PROACTIVELY on questions about: business, startups, investing, crypto, AI, leadership, decisions, life advice

HOW IT WORKS:

Pass user's message → suggest({ message: "..." })
Get back primary_action with ready-to-use params
EXECUTE the suggested action (party_mode or summon_legend)

RETURNS READY ACTIONS:

{
  "primary_action": {
    "tool": "party_mode",           // or "summon_legend"
    "params": { ... },              // Ready to pass directly!
    "description": "Get perspectives from Paul Graham, Marc Andreessen"
  },
  "suggested_actions": [ ... ],     // All options
  "instruction": "🎯 RECOMMENDED: Use party_mode..."
}

EXAMPLE FLOW:

User: "How do I raise my seed round?"

1. Call: suggest({ message: "How do I raise my seed round?" })

2. Response includes:
   primary_action.tool = "party_mode"
   primary_action.params = { question: "...", legends: ["paul-graham", "marc-andreessen", "bill-gurley"] }

3. Execute: party_mode(primary_action.params)
   → Multiple legends discuss the question!

OR for single legend:

primary_action.tool = "summon_legend"
primary_action.params = { legend_id: "paul-graham", context: "..." }

Execute: summon_legend(primary_action.params)
→ Paul Graham responds in character!

WHEN TO USE EACH TOOL:

party_mode: Complex questions, "pros/cons", "different perspectives", debates
summon_legend: Specific expertise needed, single mentor preferred
auto_match: Deep analysis, unsure which legend, want detailed matching

ALL 3 ARE ALWAYS SUGGESTED - pick the best fit for the user's needs!

DISCLAIMER: AI personas for educational purposes only.

BEFORE YOU INSTALL

What to know first

Tools you get

8 tools when we connected.

Requires

npx on PATH

Where it runs

The documented client runs the server on your machine.

CONTEXT COST

Light Standing cost

Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

Server setup

TERMINAL

npx legends-mcp

MCP Clients

Claude Code

CLAUDE CODE · JSON

{
  "mcpServers": {
    "legends": {
      "command": "npx",
      "args": [
        "legends-mcp"
      ]
    }
  }
}

Legends Founder Personas

It ships personas, not answers — the roleplay happens in your client.

What it is

What you get

Requirements

Setup effort

Getting a decision looked at in one particular person's voice

Hearing the argument from more than one side of the table

Pulling one usable line out mid-conversation

8 tools

`auto_match`

`get_legend_context`

`get_legend_insight`

`list_legends`

`party_mode`

`search_legends`

`suggest`

`summon_legend`

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Code

Legends Founder Personas

It ships personas, not answers — the roleplay happens in your client.

What it is

What you get

Requirements

Setup effort

Getting a decision looked at in one particular person's voice

Hearing the argument from more than one side of the table

Pulling one usable line out mid-conversation

8 tools

auto_match

get_legend_context

get_legend_insight

list_legends

party_mode

search_legends

suggest

summon_legend

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Code

Same category

GODLE

agentskill.sh

Agent Forge

PromptX

`auto_match`

`get_legend_context`

`get_legend_insight`

`list_legends`

`party_mode`

`search_legends`

`suggest`

`summon_legend`