Back to directory
heratiki/locallama-mcp

heratiki/locallama-mcp

@Heratiki

An MCP Server that works with Roo Code/Cline.Bot/Claude Desktop to optimize costs by intelligently routing coding tasks between local LLMs, free APIs and paid APIs.

mcpllmlocal-llmollamalm-studioopenroutercost-optimizationtask-routingtool

Installation & Configuration

{
  "mcpServers": {
    "locallama": {
      "command": "node",
      "args": [
        "/path/to/locallama-mcp/dist/index.js"
      ],
      "env": {
        "LM_STUDIO_ENDPOINT": "http://localhost:1234/v1",
        "OLLAMA_ENDPOINT": "http://localhost:11434/api",
        "DEFAULT_LOCAL_MODEL": "qwen2.5-coder-3b-instruct",
        "TOKEN_THRESHOLD": "1500",
        "COST_THRESHOLD": "0.02",
        "QUALITY_THRESHOLD": "0.07",
        "OPENROUTER_API_KEY": "your_openrouter_api_key_here"
      }
    }
  }
}

Information

Transport
stdio
Language
TypeScript
Created
2026/6/17
Updated
2026/6/17