Kognamcp

🚀 Kogna MCP Server

A Model Context Protocol (MCP) server that offers tools for interacting with Kogna's multi - agent AI avatar system. It simplifies the process of communicating with Kogna's backend and enables seamless interaction with AI avatars.

🚀 Quick Start

This guide will walk you through the installation, testing, configuration, and usage of the Kogna MCP Server.

✨ Features

• Multi - Agent Interaction: Facilitates communication with Kogna's multi - agent AI avatar system.
• Tool - Rich: Provides a variety of tools for different interaction scenarios, such as starting conversations, sending messages, and listing available avatars.

📦 Installation

Install pipx (if you don't have it)

# macOS
brew install pipx

# Other systems
pip install pipx

# Add pipx to your PATH (if not already done)
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
source ~/.zshrc

Install kognamcp

pipx install kognamcp

💻 Usage Examples

Testing the Installation

1. Test the command is available

kognamcp --help

You should see:

usage: kognamcp [-h]

Kogna MCP Bridge - Forwards MCP requests to the Kogna HTTP server

options:
  -h, --help  show this help message and exit

Examples:
  # Run as MCP server (reads from stdin, writes to stdout)
  kognamcp
  
  # Test with echo (for development)
  echo '{"jsonrpc": "2.0", "method": "initialize", "id": 1}' | kognamcp

2. Test the MCP bridge connection

echo '{"jsonrpc": "2.0", "method": "initialize", "id": 1}' | kognamcp

You should get a response like:

{"jsonrpc": "2.0", "id": 1, "result": {"protocolVersion": "2024-11-05", "capabilities": {"tools": {}}, "serverInfo": {"name": "kognamcp-server", "version": "1.0.0"}}}

Configuration

Find the kognamcp path

First, find the full path to the kognamcp command:

which kognamcp

This will output something like /Users/username/.local/bin/kognamcp

Configure your MCP client

Add this configuration to your MCP client:

{
  "mcpServers": {
    "kognamcp": {
      "command": "FULL_PATH_FROM_WHICH_COMMAND"
    }
  }
}

Replace FULL_PATH_FROM_WHICH_COMMAND with the output from which kognamcp

For example, if which kognamcp returns /Users/john/.local/bin/kognamcp, your config should be:

{
  "mcpServers": {
    "kognamcp": {
      "command": "/Users/john/.local/bin/kognamcp"
    }
  }
}

Usage

Once configured, you can use Kogna through your MCP client:

• "Start a Kogna conversation"
• "List the available Kogna avatars"
• "Switch to the business room"
• "Ask the strategist avatar about market positioning"

📚 Documentation

Troubleshooting

"Command not found: kognamcp"

1. Make sure the installation completed successfully:

   pipx list | grep kognamcp
   

2. Add pipx to your PATH:

   echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.zshrc
   source ~/.zshrc
   

3. Restart your terminal/IDE

"spawn kognamcp ENOENT" or similar errors

This happens when your MCP client can't find the kognamcp command. The solution is to use the full path:

1. Find the full path:

   which kognamcp
   

2. Copy the exact output and use it in your MCP configuration

3. Restart your MCP client

Connection errors

The bridge connects to https://kogna.up.railway.app/mcp. Make sure you have internet access.

Available Tools

• start_kogna_conversation - Start a new conversation with Kogna avatars
• send_kogna_message - Send a message to the current conversation
• list_kogna_avatars - List available avatars and their specialties
• list_kogna_rooms - List available rooms and their descriptions
• switch_kogna_avatar - Switch to a different avatar
• switch_kogna_room - Switch to a different room
• get_kogna_conversation_history - Get conversation history
• get_kogna_system_info - Get system information

Requirements

• Python 3.8+
• Internet connection (connects to Kogna backend)

📄 License

MIT License