Skip to content
Cline

ollama handoff for Cline

io.github.michael-whitecapdata/ollama-handoff

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

client:Cline transport:stdio runtime:pypi

Install ollama handoff in Cline

~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json · windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json

Held in this page only — never stored, logged, or sent anywhere but back to your screen.

{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "<OLLAMA_URL>",
        "OLLAMA_DEFAULT_MODEL": "<OLLAMA_DEFAULT_MODEL>",
        "OLLAMA_NUM_CTX": "<OLLAMA_NUM_CTX>",
        "OLLAMA_KEEP_ALIVE": "<OLLAMA_KEEP_ALIVE>",
        "OLLAMA_TIMEOUT_S": "<OLLAMA_TIMEOUT_S>"
      }
    }
  }
}

Cline's MCP Servers pane edits this file for you if you would rather not find it. Cline docs

ollama handoff in other clients