Ollama Handoff MCP Server

An MCP server that offloads cheap work from your cloud LLM agent to a local Ollama model. Its 8 documented tools cluster into ask, chat, summarize, code.

People connecting AI & ML tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-06-23 · ★ 3 · #60 OF 95 MAINTAINED AI & ML · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Ollama Handoff

before you install - you'll need

Set OLLAMA_URL before connecting. OLLAMA_DEFAULT_MODEL is optional or environment-specific per the README.

Claude Code

claude mcp add michael-whitecapdata-ollama-handoff -- uvx ollama-handoff

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "michael-whitecapdata-ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package ollama-handoff - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.Michael-WhiteCapData is GitHub-verified and matches the repo owner

03 · What Ollama Handoff can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can list locally available Ollama models, and report the effective configuration.

Capability map

Tools grouped from the project's README - what Ollama Handoff lets an agent do.

Ask

1 tool - e.g. One-shot prompt to the local model

ask_local

Chat

1 tool - e.g. Multi-turn local chat

chat_local

Summarize

1 tool - e.g. Structured summary (headline + bullets)

summarize_local

Code

1 tool - e.g. Quick first-pass review of a diff/code

code_review_local

Draft

1 tool - e.g. Conventional commit message from a diff

draft_commit_message_local

Extract

1 tool - e.g. Pull structured items from unstructured text

extract_local

read & search

1 tool - e.g. List locally available Ollama models

list_models

Server

1 tool - e.g. Report the effective configuration

server_info

04 · Who maintains Ollama Handoff

ollama-handoff is maintained by michael-whitecapdata. We track 3 MCP servers from michael-whitecapdata - 3 actively maintained, 7 combined GitHub stars, oldest repo from Jun 2026. Full record: all servers from michael-whitecapdata.

05 · Facts

repository: github.com/michael-whitecapdata/ollama-handoff
category: AI & ML - ranked #60 of 95 actively-maintained AI & ML servers as of 2026-08-25.
registry: io.github.Michael-WhiteCapData/ollama-handoff (active, first published 2026-06-21 · 2 versions)
packages: pypi:ollama-handoff

06 · Ollama Handoff FAQ

Is Ollama Handoff still maintained?

Yes - as of 2026-08-25, its last commit was 2026-06-23. We re-verify nightly.

What can Ollama Handoff do?

With this server connected, an agent can list locally available Ollama models, and report the effective configuration.

How do I install Ollama Handoff?

Run `uvx ollama-handoff`. The README documents 2 environment variables (OLLAMA_DEFAULT_MODEL, OLLAMA_URL) to set first. Set OLLAMA_URL before connecting. OLLAMA_DEFAULT_MODEL is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Ollama Handoff run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Ollama Handoff

Alternatives to Ollama Handoff

Maintained AI & ML servers if Ollama Handoff isn't the fit.

Pairs well with

Servers that cover what Ollama Handoff doesn't - only shown when the pairing reason fits the companion.

More AI & ML MCP servers · Claude Prompts MCP · Grantex · Mercury Spec Ops · Diffctx

More Python MCP servers · Tablebridge MCP · White Cap Data Dev · Quanttogo MCP (michaeljiangmingfeng-debug) · Zendesk MCP · MidOS - MCP Community Library · see all