Local AI MCP

io.github.TMHSDigital/local-ai-mcp · v0.6.1

Run, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).

Website Source code Set it up

Connect Runs on your machine

Terminal

claude mcp add local-ai-mcp -e OLLAMA_HOST=<OLLAMA_HOST> -e LMSTUDIO_HOST=<LMSTUDIO_HOST> -e LLAMACPP_HOST=<LLAMACPP_HOST> -e DOCKER_MODEL_RUNNER_HOST=<DOCKER_MODEL_RUNNER_HOST> -e MLX_HOST=<MLX_HOST> -e VLLM_HOST=<VLLM_HOST> -e VLLM_API_KEY=<VLLM_API_KEY> -e FOUNDRY_LOCAL_HOST=<FOUNDRY_LOCAL_HOST> -e OPENAI_COMPAT_HOST=<OPENAI_COMPAT_HOST> -e OPENAI_COMPAT_API_KEY=<OPENAI_COMPAT_API_KEY> -e MOONSHOT_API_KEY=<MOONSHOT_API_KEY> -e LOCAL_AI_ALLOW_HOSTED_FALLBACK=<LOCAL_AI_ALLOW_HOSTED_FALLBACK> -e MOONSHOT_HOST=<MOONSHOT_HOST> -e LOCAL_AI_DISABLE=<LOCAL_AI_DISABLE> -e LOCAL_AI_PROVIDERS=<LOCAL_AI_PROVIDERS> -e LOCAL_AI_DISABLE_NETWORK_SEARCH=<LOCAL_AI_DISABLE_NETWORK_SEARCH> -e LOCAL_AI_BENCHMARK_CACHE=<LOCAL_AI_BENCHMARK_CACHE> -- npx -y @tmhs/[email protected]

claude_desktop_config.json

{
  "mcpServers": {
    "local-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/[email protected]"
      ],
      "env": {
        "OLLAMA_HOST": "<OLLAMA_HOST>",
        "LMSTUDIO_HOST": "<LMSTUDIO_HOST>",
        "LLAMACPP_HOST": "<LLAMACPP_HOST>",
        "DOCKER_MODEL_RUNNER_HOST": "<DOCKER_MODEL_RUNNER_HOST>",
        "MLX_HOST": "<MLX_HOST>",
        "VLLM_HOST": "<VLLM_HOST>",
        "VLLM_API_KEY": "<VLLM_API_KEY>",
        "FOUNDRY_LOCAL_HOST": "<FOUNDRY_LOCAL_HOST>",
        "OPENAI_COMPAT_HOST": "<OPENAI_COMPAT_HOST>",
        "OPENAI_COMPAT_API_KEY": "<OPENAI_COMPAT_API_KEY>",
        "MOONSHOT_API_KEY": "<MOONSHOT_API_KEY>",
        "LOCAL_AI_ALLOW_HOSTED_FALLBACK": "<LOCAL_AI_ALLOW_HOSTED_FALLBACK>",
        "MOONSHOT_HOST": "<MOONSHOT_HOST>",
        "LOCAL_AI_DISABLE": "<LOCAL_AI_DISABLE>",
        "LOCAL_AI_PROVIDERS": "<LOCAL_AI_PROVIDERS>",
        "LOCAL_AI_DISABLE_NETWORK_SEARCH": "<LOCAL_AI_DISABLE_NETWORK_SEARCH>",
        "LOCAL_AI_BENCHMARK_CACHE": "<LOCAL_AI_BENCHMARK_CACHE>"
      }
    }
  }
}

~/.cursor/mcp.json

{
  "mcpServers": {
    "local-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/[email protected]"
      ],
      "env": {
        "OLLAMA_HOST": "<OLLAMA_HOST>",
        "LMSTUDIO_HOST": "<LMSTUDIO_HOST>",
        "LLAMACPP_HOST": "<LLAMACPP_HOST>",
        "DOCKER_MODEL_RUNNER_HOST": "<DOCKER_MODEL_RUNNER_HOST>",
        "MLX_HOST": "<MLX_HOST>",
        "VLLM_HOST": "<VLLM_HOST>",
        "VLLM_API_KEY": "<VLLM_API_KEY>",
        "FOUNDRY_LOCAL_HOST": "<FOUNDRY_LOCAL_HOST>",
        "OPENAI_COMPAT_HOST": "<OPENAI_COMPAT_HOST>",
        "OPENAI_COMPAT_API_KEY": "<OPENAI_COMPAT_API_KEY>",
        "MOONSHOT_API_KEY": "<MOONSHOT_API_KEY>",
        "LOCAL_AI_ALLOW_HOSTED_FALLBACK": "<LOCAL_AI_ALLOW_HOSTED_FALLBACK>",
        "MOONSHOT_HOST": "<MOONSHOT_HOST>",
        "LOCAL_AI_DISABLE": "<LOCAL_AI_DISABLE>",
        "LOCAL_AI_PROVIDERS": "<LOCAL_AI_PROVIDERS>",
        "LOCAL_AI_DISABLE_NETWORK_SEARCH": "<LOCAL_AI_DISABLE_NETWORK_SEARCH>",
        "LOCAL_AI_BENCHMARK_CACHE": "<LOCAL_AI_BENCHMARK_CACHE>"
      }
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "local-ai-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/[email protected]"
      ],
      "env": {
        "OLLAMA_HOST": "<OLLAMA_HOST>",
        "LMSTUDIO_HOST": "<LMSTUDIO_HOST>",
        "LLAMACPP_HOST": "<LLAMACPP_HOST>",
        "DOCKER_MODEL_RUNNER_HOST": "<DOCKER_MODEL_RUNNER_HOST>",
        "MLX_HOST": "<MLX_HOST>",
        "VLLM_HOST": "<VLLM_HOST>",
        "VLLM_API_KEY": "<VLLM_API_KEY>",
        "FOUNDRY_LOCAL_HOST": "<FOUNDRY_LOCAL_HOST>",
        "OPENAI_COMPAT_HOST": "<OPENAI_COMPAT_HOST>",
        "OPENAI_COMPAT_API_KEY": "<OPENAI_COMPAT_API_KEY>",
        "MOONSHOT_API_KEY": "<MOONSHOT_API_KEY>",
        "LOCAL_AI_ALLOW_HOSTED_FALLBACK": "<LOCAL_AI_ALLOW_HOSTED_FALLBACK>",
        "MOONSHOT_HOST": "<MOONSHOT_HOST>",
        "LOCAL_AI_DISABLE": "<LOCAL_AI_DISABLE>",
        "LOCAL_AI_PROVIDERS": "<LOCAL_AI_PROVIDERS>",
        "LOCAL_AI_DISABLE_NETWORK_SEARCH": "<LOCAL_AI_DISABLE_NETWORK_SEARCH>",
        "LOCAL_AI_BENCHMARK_CACHE": "<LOCAL_AI_BENCHMARK_CACHE>"
      }
    }
  }
}

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools

This server runs locally, so its tools are listed by your MCP client once it starts.

Environment variables

Name	Description
`OLLAMA_HOST` Optional	Ollama base URL
`LMSTUDIO_HOST` Optional	LM Studio server base URL
`LLAMACPP_HOST` Optional	llama.cpp server (llama-server) base URL
`DOCKER_MODEL_RUNNER_HOST` Optional	Docker Model Runner host TCP endpoint
`MLX_HOST` Optional	mlx_lm.server base URL (opt-in; Apple Silicon)
`VLLM_HOST` Optional	vLLM OpenAI server base URL (opt-in)
`VLLM_API_KEY` Optional, secret	Bearer token for VLLM_HOST (when vLLM runs with --api-key)
`FOUNDRY_LOCAL_HOST` Optional	Foundry Local service URL (opt-in; port from `foundry service status`)
`OPENAI_COMPAT_HOST` Optional	Any OpenAI-compatible /v1 server (opt-in)
`OPENAI_COMPAT_API_KEY` Optional, secret	Bearer token for OPENAI_COMPAT_HOST
`MOONSHOT_API_KEY` Optional, secret	Moonshot AI (Kimi) key. Hosted: only used when named explicitly.
`LOCAL_AI_ALLOW_HOSTED_FALLBACK` Optional	Allow implicit routing to hosted providers (default: off)
`MOONSHOT_HOST` Optional	Moonshot API base URL
`LOCAL_AI_DISABLE` Optional	Comma-separated provider names to skip probing
`LOCAL_AI_PROVIDERS` Optional	JSON array of extra provider instances: {type, host, name?, apiKey?, kind?}
`LOCAL_AI_DISABLE_NETWORK_SEARCH` Optional	Keep search_models offline (catalog only)
`LOCAL_AI_BENCHMARK_CACHE` Optional	Benchmark results file used to rank delegate by measured speed (default: per-user cache dir; off disables)

Details

Package	`@tmhs/[email protected]` (NPM, stdio)
First published	3 Nov 2026
Last updated	3 Nov 2026
Registry name	`io.github.TMHSDigital/local-ai-mcp`

More other servers See all

Live status

Local install

Installed and run on your own machine, so there is no public endpoint to check.

Pair it with live search

Agents that use Local AI MCP often also need current facts. NestDaddy MCP gives your AI today's internet: web search, real-time breaking news and full page reading in one connector.

See NestDaddy MCP

For maintainers

[![NestDaddy MCP](https://nestdaddy.com/mcp/servers/io-github-tmhsdigital-local-ai-mcp/badge.svg)](https://nestdaddy.com/mcp/servers/io-github-tmhsdigital-local-ai-mcp)

Add the badge to your README. It turns green while your server passes our daily check. Listing details come from the official MCP registry; update them there.

Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.