ollama-handoff

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "name": "io.github.Michael-WhiteCapData/ollama-handoff",
  "description": "Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.",
  "repository": {
    "url": "https://github.com/Michael-WhiteCapData/ollama-handoff",
    "source": "github"
  },
  "version": "0.1.2",
  "packages": [
    {
      "registryType": "pypi",
      "identifier": "ollama-handoff",
      "version": "0.1.2",
      "transport": {
        "type": "stdio"
      },
      "environmentVariables": [
        {
          "description": "Base URL of the Ollama server.",
          "default": "http://localhost:11434",
          "name": "OLLAMA_URL"
        },
        {
          "description": "Default model used for handoffs.",
          "default": "qwen2.5-coder:14b",
          "name": "OLLAMA_DEFAULT_MODEL"
        },
        {
          "description": "Context window in tokens.",
          "default": "32768",
          "name": "OLLAMA_NUM_CTX"
        },
        {
          "description": "How long to keep the model resident in VRAM.",
          "default": "30m",
          "name": "OLLAMA_KEEP_ALIVE"
        },
        {
          "description": "Per-request timeout in seconds.",
          "default": "600",
          "name": "OLLAMA_TIMEOUT_S"
        }
      ]
    }
  ]
}