Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
The publisher's own command. Not a PlugMCP endpoint.
uvx ollama-handoff==0.1.2
OLLAMA_URL=<value> OLLAMA_DEFAULT_MODEL=<value> OLLAMA_NUM_CTX=<value> OLLAMA_KEEP_ALIVE=<value> OLLAMA_TIMEOUT_S=<value> claude mcp add io.github.michael-whitecapdata-ollama-handoff -- uvx ollama-handoff==0.1.2
Run in a terminal.
{
"mcpServers": {
"io.github.michael-whitecapdata-ollama-handoff": {
"command": "uvx",
"args": [
"ollama-handoff==0.1.2"
],
"env": {
"OLLAMA_URL": "<value>",
"OLLAMA_DEFAULT_MODEL": "<value>",
"OLLAMA_NUM_CTX": "<value>",
"OLLAMA_KEEP_ALIVE": "<value>",
"OLLAMA_TIMEOUT_S": "<value>"
}
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchOffload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
README is not crawled yet. Open the repository
No tool list yet. Remote servers get one after the first health check.