Ollama MCP

A self-contained MCP server for managing local Ollama models with no external dependencies. Agents can list installed models, pull or remove them, start and stop the Ollama server, run local completions, and use a model-advisor tool that recommends which locally available model best fits a given task.

{
  "mcpServers": {
    "ollama": {
      "command": "npx",
      "args": [],
      "env": {
        "OLLAMA_HOST": "<YOUR_OLLAMA_HOST>"
      }
    }
  }
}

{
  "type": "object",
  "properties": {}
}

{
  "type": "object",
  "required": [
    "model"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Model name to pull (e.g. llama3.1:8b)"
    }
  }
}

{
  "type": "object",
  "required": [
    "model",
    "prompt"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "Local model name"
    },
    "prompt": {
      "type": "string",
      "description": "Prompt text"
    }
  }
}