NestDaddy

Ollama Handoff

io.github.Michael-WhiteCapData/ollama-handoff ยท v0.1.2

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

Connect Runs on your machine

Terminal
claude mcp add ollama-handoff -e OLLAMA_URL=<OLLAMA_URL> -e OLLAMA_DEFAULT_MODEL=<OLLAMA_DEFAULT_MODEL> -e OLLAMA_NUM_CTX=<OLLAMA_NUM_CTX> -e OLLAMA_KEEP_ALIVE=<OLLAMA_KEEP_ALIVE> -e OLLAMA_TIMEOUT_S=<OLLAMA_TIMEOUT_S> -- uvx ollama-handoff==0.1.2
claude_desktop_config.json
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff==0.1.2"
      ],
      "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>"
      }
    }
  }
}
~/.cursor/mcp.json
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff==0.1.2"
      ],
      "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>"
      }
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "ollama-handoff": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ollama-handoff==0.1.2"
      ],
      "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>"
      }
    }
  }
}

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Environment variables

NameDescription
OLLAMA_URL
Optional
Base URL of the Ollama server.
OLLAMA_DEFAULT_MODEL
Optional
Default model used for handoffs.
OLLAMA_NUM_CTX
Optional
Context window in tokens.
OLLAMA_KEEP_ALIVE
Optional
How long to keep the model resident in VRAM.
OLLAMA_TIMEOUT_S
Optional
Per-request timeout in seconds.

Details

Package[email protected] (PYPI, stdio)
First published23 Jun 2026
Last updated23 Jun 2026
Registry nameio.github.Michael-WhiteCapData/ollama-handoff

More ai and media servers See all

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.