Ollama MCP Server

by lykhoydaio.github.Lykhoyda/ask-ollamav0.7.0

Bridge Claude with local Ollama LLMs for private AI-to-AI collaboration — no API keys, fully local

18Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Active3d ago

Install Ollama MCP server

claude mcp add ollama -- npx -y @ask-llm/ollama-mcp

{
  "mcpServers": {
    "ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/ollama-mcp"
      ]
    }
  }
}

Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).

{
  "mcpServers": {
    "ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/ollama-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config (claude_desktop_config.json), then restart.

{
  "servers": {
    "ollama": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/ollama-mcp"
      ]
    }
  }
}

Add to .vscode/mcp.json in your workspace.

{
  "mcpServers": {
    "ollama": {
      "command": "npx",
      "args": [
        "-y",
        "@ask-llm/ollama-mcp"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json.

Configuration

Variable	Required	Secret	Description
OLLAMA_HOST	—	—	Ollama server address (default: http://localhost:11434)
GMCPT_TIMEOUT_MS	—	—	Timeout for Ollama execution in milliseconds (default: 300000 = 5 minutes)
GMCPT_LOG_LEVEL	—	—	Log verbosity: debug, info, warn, error (default: warn)