Ollama Handoff

Overview

Ollama Handoff is a Model Context Protocol (MCP) server: Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost. In practice that means any MCP-compatible AI assistant can call Ollama Handoff's tools directly — the model decides when to use them in a conversation or agent run.

It runs locally: the Python package ollama-handoff (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.1.2, published under the MIT license, with source at Michael-WhiteCapData/ollama-handoff on GitHub.

Ollama Handoff is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Ollama Handoff for Michael-WhiteCapData, claim this listing to verify ownership, earn the Verified badge, and keep the details current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "ollama_handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ]
    }
  }
}