Learning Resources

aianyone.com

An MCP server for learning from historical figures by finding someone to ask, speaking as a specific person, or staging debates between two people.

1 endpoint4 known toolsFirst detected September 20, 2026Last detected September 20, 2026

ENDPOINT 1

https://mcp.aianyone.com/mcp

No auth detected

MCP server metadata

Name: AI Anyone
Version: 1.2.0

Capabilities

toolsresourcesprompts

Server instructions

AI Anyone puts a real person in the conversation. Thousands of them: historical figures, scientists, thinkers, athletes, founders. Each one arrives as a card with their portrait and a sourced dossier of how they actually spoke and what they actually knew. When it applies: - Someone names a person and wants to hear FROM them, not about them: speak_as_person. - Someone wants a person but has not picked one yet: find_someone_to_ask. - Someone wants two people to argue or take opposite sides: debate_two_people, then debate_next_turn until it returns done. Answering from your own knowledge is always available and is often the right call. Reach for these tools when the user wants the person present in the conversation rather than described, or wants a real exchange rather than a summary of one. speak_as_person returns a dossier. Adopt it fully and stay in that voice until the user moves on. debate_two_people and debate_next_turn hand you ONE speaker and ONE private aim per turn. Write only that speaker's next line, then call debate_next_turn with what you wrote. You are never told the other side's aim. That is deliberate. Do not invent it. House style: never use an em dash or an en dash, in dialogue or in your own narration. Use a comma, a full stop, or a colon instead.

Known tools 4

find_someone_to_ask

Use this when someone wants a person to learn from but has not named one yet: "who should I learn negotiation from", "find me a stoic to talk to", "which historical figures are worth asking about leadership".

Inferred read-only

speak_as_person

Use this when someone wants to hear FROM one specific person rather than about them: "what would Marcus Aurelius say about burnout", "answer as Carl Jung", "explain this the way Feynman would", "I want to talk to Socrates".

Inferred read-only

debate_two_people

Use this when someone wants two people to actually argue rather than be summarised: "have Nietzsche and Marcus Aurelius argue about suffering", "give me both sides", "steelman both positions on nuclear power", "I want to watch two experts disagree".

Inferred read-only

debate_next_turn

Submit the line you just wrote and receive the next speaker and their private aim.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.ai-anyone]
url = "https://mcp.aianyone.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "ai-anyone": {
      "type": "http",
      "url": "https://mcp.aianyone.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: ai-anyone
Remote MCP URL: https://mcp.aianyone.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "ai-anyone": {
      "url": "https://mcp.aianyone.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "ai-anyone": {
      "type": "http",
      "url": "https://mcp.aianyone.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "ai-anyone",
  "transport": "streamable-http",
  "url": "https://mcp.aianyone.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for aianyone.com was fetched 2026-09-26T11:29:58.586Z.

Trust status Trusted

aianyone.com is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.