HotStack

← Back to browse

ollama-handoff

Indexed by io.github.Michael-WhiteCapData
View source ↗

About

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

Use this server

Add it to your MCP client. The catalogue lists this config verbatim from its source — it does not run, download, or vouch for the server. Review the command before you run it.

Transportstdio (runs a local command)
Env varsOLLAMA_URL OLLAMA_DEFAULT_MODEL OLLAMA_NUM_CTX OLLAMA_KEEP_ALIVE OLLAMA_TIMEOUT_S
Claude Code 
claude mcp add --env OLLAMA_URL= --env OLLAMA_DEFAULT_MODEL= --env OLLAMA_NUM_CTX= --env OLLAMA_KEEP_ALIVE= --env OLLAMA_TIMEOUT_S= ollama-handoff -- uvx ollama-handoff
Cursor

Add to Cursor

If the button doesn't open Cursor, use the JSON below — Cursor accepts the same mcpServers config.

VS Code 
code --add-mcp '{"name":"ollama-handoff","command":"uvx","args":["ollama-handoff"],"env":{"OLLAMA_URL":"","OLLAMA_DEFAULT_MODEL":"","OLLAMA_NUM_CTX":"","OLLAMA_KEEP_ALIVE":"","OLLAMA_TIMEOUT_S":""}}'
JSON 
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "",
        "OLLAMA_DEFAULT_MODEL": "",
        "OLLAMA_NUM_CTX": "",
        "OLLAMA_KEEP_ALIVE": "",
        "OLLAMA_TIMEOUT_S": ""
      }
    }
  }
}

Environment variables are listed by name only — fill in your own values. Entries never carry secrets.