KognitiveKompanion

KDE AI Interface and MCP Server Integration

Catalog onlyCatalog onlySTDIO

Overview

KognitiveKompanion is a modern AI interface designed for KDE and other desktop environments, enabling seamless interaction with various AI backends such as OpenAI, Ollama, and AMD Ryzen AI hardware.

To use KognitiveKompanion, clone the repository from GitHub, install the required dependencies, and run the application with your preferred AI backend.

Multi-backend support including OpenAI API and local models. - Advanced user interface with collapsible sections and conversation management. - Context features like screen capture and audio input support.

Integrating AI capabilities into KDE desktop environments.
Utilizing local AI models for privacy-focused applications.
Enhancing user interaction with AI through advanced UI features.

Add to your AI client

Use these steps to connect KognitiveKompanion in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "kognitivekompanion-skybehind": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "kognitivekompanion-skybehind": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "kognitivekompanion-skybehind": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "kognitivekompanion-skybehind": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "kognitivekompanion-skybehind": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "kognitivekompanion-skybehind": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-kognitivekompanion-skybehind"
      ]
    }
  }
}

FAQ

What backends does KognitiveKompanion support?

It supports OpenAI API, Ollama for local models, and AMD Ryzen AI hardware.

Is KognitiveKompanion free to use?

Yes, it is open-source and free to use under the MIT License.

Can I run KognitiveKompanion on desktops other than KDE?

Yes, while optimized for KDE, it can work on other desktop environments as well.

Developer tools