PluginBench
MCP Server
Active
MIT

io.github.Michael-WhiteCapData/ollama-handoff MCP Server

io.github.Michael-WhiteCapData/ollama-handoff

RepositoryRegistry

What is the io.github.Michael-WhiteCapData/ollama-handoff MCP server?

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

How to install io.github.Michael-WhiteCapData/ollama-handoff

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • OLLAMA_URL

    Base URL of the Ollama server.

  • OLLAMA_DEFAULT_MODEL

    Default model used for handoffs.

  • OLLAMA_NUM_CTX

    Context window in tokens.

  • OLLAMA_KEEP_ALIVE

    How long to keep the model resident in VRAM.

  • OLLAMA_TIMEOUT_S

    Per-request timeout in seconds.

Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "OLLAMA_DEFAULT_MODEL": "<YOUR_OLLAMA_DEFAULT_MODEL>",
        "OLLAMA_NUM_CTX": "<YOUR_OLLAMA_NUM_CTX>",
        "OLLAMA_KEEP_ALIVE": "<YOUR_OLLAMA_KEEP_ALIVE>",
        "OLLAMA_TIMEOUT_S": "<YOUR_OLLAMA_TIMEOUT_S>"
      }
    }
  }
}
Cursor
~/.cursor/mcp.json
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "OLLAMA_DEFAULT_MODEL": "<YOUR_OLLAMA_DEFAULT_MODEL>",
        "OLLAMA_NUM_CTX": "<YOUR_OLLAMA_NUM_CTX>",
        "OLLAMA_KEEP_ALIVE": "<YOUR_OLLAMA_KEEP_ALIVE>",
        "OLLAMA_TIMEOUT_S": "<YOUR_OLLAMA_TIMEOUT_S>"
      }
    }
  }
}
Windsurf
~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "ollama-handoff": {
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "OLLAMA_DEFAULT_MODEL": "<YOUR_OLLAMA_DEFAULT_MODEL>",
        "OLLAMA_NUM_CTX": "<YOUR_OLLAMA_NUM_CTX>",
        "OLLAMA_KEEP_ALIVE": "<YOUR_OLLAMA_KEEP_ALIVE>",
        "OLLAMA_TIMEOUT_S": "<YOUR_OLLAMA_TIMEOUT_S>"
      }
    }
  }
}
VS Code
.vscode/mcp.json
{
  "servers": {
    "ollama-handoff": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "ollama-handoff"
      ],
      "env": {
        "OLLAMA_URL": "<YOUR_OLLAMA_URL>",
        "OLLAMA_DEFAULT_MODEL": "<YOUR_OLLAMA_DEFAULT_MODEL>",
        "OLLAMA_NUM_CTX": "<YOUR_OLLAMA_NUM_CTX>",
        "OLLAMA_KEEP_ALIVE": "<YOUR_OLLAMA_KEEP_ALIVE>",
        "OLLAMA_TIMEOUT_S": "<YOUR_OLLAMA_TIMEOUT_S>"
      }
    }
  }
}
Claude Code
claude mcp add ollama-handoff --env OLLAMA_URL=<YOUR_OLLAMA_URL> --env OLLAMA_DEFAULT_MODEL=<YOUR_OLLAMA_DEFAULT_MODEL> --env OLLAMA_NUM_CTX=<YOUR_OLLAMA_NUM_CTX> --env OLLAMA_KEEP_ALIVE=<YOUR_OLLAMA_KEEP_ALIVE> --env OLLAMA_TIMEOUT_S=<YOUR_OLLAMA_TIMEOUT_S> -- uvx ollama-handoff

Related MCP servers

io.github.Michael-WhiteCapData/tablebridge-mcp

Active

Query a folder of CSV / Parquet / JSON files with SQL — one queryable source, read-only.

2
Python
MIT
View repository →

io.github.Michael-WhiteCapData/WhiteCapData-Dev

Active

Operate a k3s / Kubernetes cluster from your AI agent — safe-by-default MCP server.

1
Python
MIT
View repository →