Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "ollama-code-mcp": {
      "command": "uvx",
      "args": [
        "ollama-code-mcp"
      ]
    }
  }
}

Or install with pip: pip install ollama-code-mcp

README Excerpt

An [MCP](https://modelcontextprotocol.io) server that lets Claude Code delegate coding tasks to a local (or LAN) [Ollama](https://ollama.com) instance running a Qwen3 model. Point it at a GPU box on your network -- a Tesla V100 running `qwen3-coder:30b`, for example -- and Claude Code can hand off boilerplate

Tools (20)

MCP_HOSTMCP_PORTMCP_TRANSPORTOLLAMA_BASE_URLOLLAMA_CONNECT_TIMEOUTOLLAMA_MCP_ALLOWED_DIROLLAMA_MCP_DEFAULT_THINKOLLAMA_MCP_MAX_BATCH_FILESOLLAMA_MCP_MAX_FILE_BYTESOLLAMA_MODELOLLAMA_NUM_CTXOLLAMA_THINK_STYLEOLLAMA_TIMEOUTbatch_refactorcode_review_diffexplain_codefix_codegenerate_codeollama_statusqwen

Topics

ai-agentsclaudeclaude-codek3skubernetesllmlocal-llmmcpmcp-servermodel-context-protocolollamapythonqwenself-hosted

ollama-code-mcp

Quick Install

README Excerpt

Tools (20)

Topics

Related AI/LLM Servers