Quick Install

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

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "local-llm-mcp": {
      "command": "uvx",
      "args": [
        "local-llm-mcp"
      ]
    }
  }
}

Or install with pip: pip install local-llm-mcp

README Excerpt

A production-grade FastMCP server for managing local and cloud LLMs: Ollama, vLLM, LM Studio, and 28 cloud providers through a unified AI gateway. Includes a SOTA React/Vite dashboard, provider health monitoring with circuit breakers, and LM Link peer discovery over Tailscale. ``` Ports: 10832 (dashboard frontend) 10833 (dashboard API + gateway)

Tools (19)

LLM_MCP_ENABLE_LEGACY_TOOLSLLM_MCP_LOG_LEVELMCP_HOSTMCP_PORTMCP_TRANSPORTlatency_msllm_enginellm_finetuningllm_generationllm_google_cloudllm_gpullm_healthllm_helpllm_huggingfacellm_lmstudiollm_modelsllm_multimodalllm_ollamallm_vllm

Topics

fastmcpllmlocalmcppython

local-llm-mcp

Quick Install

README Excerpt

Tools (19)

Topics

Related AI/LLM Servers