LLM reasoning regime detection, cross-domain pattern transfer, and model routing.
uvx kongenlabs-mcp{
"KONGEN_API_KEY": "YOUR_SECRET_VALUE"
}Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.
{
"mcpServers": {
"io-github-fisnik-kongen-mcp": {
"command": "uvx",
"args": [
"kongenlabs-mcp"
],
"env": {
"KONGEN_API_KEY": "YOUR_SECRET_VALUE"
}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.jsonNo remote HTTP endpoint is advertised. Use the package or stdio setup shown in Install.
Kongen Labs — Pattern Intelligence is an MCP server for LLM reasoning regime detection, cross-domain pattern transfer, and model routing.. It supports STDIO transport.
Use the generated config in Install. This server runs with uvx kongenlabs-mcp; add any required environment variables before starting your client.
Choose the Claude Desktop tab in Install and copy the config for uvx kongenlabs-mcp. Add required environment variables before starting Claude Desktop.
Choose the Claude Code tab in Install and copy the config for uvx kongenlabs-mcp. Add required environment variables before starting Claude Code.
Choose the Codex tab in Install and copy the config for uvx kongenlabs-mcp. Add required environment variables before starting Codex.
Choose the Cursor or VS Code tab in Install and copy the config for uvx kongenlabs-mcp. Add required environment variables before starting Cursor or VS Code.
Kongen Labs — Pattern Intelligence uses STDIO transport. Use the package or command config in Install.
Kongen Labs — Pattern Intelligence inventory is listed when the MCP endpoint exposes tools, resources, or prompts. Some servers require auth first.
Kongen Labs — Pattern Intelligence is marked with Auth required by registry metadata auth. You may need provider login, an API key, a bearer token, or a session header.
| Package | Registry | Version | Inputs |
|---|---|---|---|
kongenlabs-mcpstdio | pypi | 1.0.0 | Env: KONGEN_API_KEY required secret |