Developer · Local MCP server

Ollama Handoff

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

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.Michael-WhiteCapData/ollama-handoff
Version
0.1.2
Status
Active
Category
developer
Transport
stdio (local process)
Package
PyPI
Published
2026-06-23
Updated
2026-06-23
Publisher
Michael-WhiteCapData (GitHub) · 3 servers with pages here
Repository
github.com/Michael-WhiteCapData/ollama-handoff
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
PyPIollama-handoff0.1.2stdioOLLAMA_URL, OLLAMA_DEFAULT_MODEL, OLLAMA_NUM_CTX, OLLAMA_KEEP_ALIVE, OLLAMA_TIMEOUT_S

How to connect Ollama Handoff

Ollama Handoff runs locally from a Python package published to PyPI: ollama-handoff version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx ollama-handoff. It reads these environment variables: OLLAMA_URL, OLLAMA_DEFAULT_MODEL, OLLAMA_NUM_CTX, OLLAMA_KEEP_ALIVE and OLLAMA_TIMEOUT_S; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

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

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from Michael-WhiteCapData (GitHub)

ServerRunsEndpoint or package
Tablebridge MCPQuery a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.Local · stdioPyPI: tablebridge
WhiteCapData DevOperate a k3s / Kubernetes cluster from your AI agent — safe-by-default MCP server.Local · stdioPyPI: whitecapdata-dev

More developer servers

All 6,250 →
ServerRunsEndpoint or package
OidsMCP endpoint for Oids, a microblogging network for AI agents: posts, DMs, prompt packs.Remote · HTTPapi.tryoids.com
OilpriceAPI MCP-SERVERSource-timestamped energy data and reviewed OilPriceAPI product facts for MCP clients.Local · stdionpm: oilpriceapi-mcp
okffsMCP server connecting Claude Code to GitHub for an issue to branch to PR to close workflow.Local · stdionpm: @neturely/okffs
OleanderThe all-in-one data stack for agents. Upload files, run SQL, evolve tables, and render charts.Remote · HTTPoleander.dev
OmenMulti-language code analysis for complexity, debt, hotspots, ownership, and defect prediction.Local · stdioOCI image (Docker): ghcr.io/panbanda/omen:3.0.0
Omiss MCPOMISS MCP server. Net schedule, nets on the air, members, check-in history, awards.Local · stdioPyPI: omiss-mcp
OmnaraDeploy durable AI agents with Omnara, an open-source managed-agent platform.Remote · HTTPapp.omnara.com
Omni Computer UseWindows MCP server replicating Anthropic's computer-use tool surface, for any MCP client.Local · stdioPyPI: omni-computer-use-mcp