mcpbeat Sign in

Local AI MCP Server

local only

Local AI MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 24 installs a week from npm. Last commit 3 Nov 2026.

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

Installs per day peak 13 · avg 3 · +80% w/w
a month agotoday
24
Installs / week
npm · @tmhs/local-ai-mcp
0
Stars
2 open issues
3 Nov 2026
Last commit
from GitHub
—
License
TypeScript

Nothing serious here today

Today is the operative word: we check Local AI MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

run in your terminal
claude mcp add local-ai-mcp -- npx -y @tmhs/local-ai-mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "local-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/local-ai-mcp"
      ]
    }
  }
}
~/.codex/config.toml
[mcp_servers.local-ai-mcp]
command = "npx"
args = ["-y", "@tmhs/local-ai-mcp"]
.cursor/mcp.json
{
  "mcpServers": {
    "local-ai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/local-ai-mcp"
      ]
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "local-ai-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@tmhs/local-ai-mcp"
      ]
    }
  }
}

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

Alternatives to Local AI MCP

same job, measured the same way
Qsp Client
by qso-graph

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

830 installs/wk local only
Roslyn Workbench MCP
by lantean-code

Bring Visual Studio-style C# fixes and refactorings to your AI agent with local Roslyn Code Actions.

local only
Sezzlee Local LLM
by sezzlee

Let a planning agent hand bounded language work to a local Ollama model.

62 installs/wk local only
Claude Token Saver MCP
by blackfoil

MCP server that offloads routine coding tasks to local LLM (Ollama) to save Claude API tokens

501 installs/wk local only
Wiro AI
by wiro

Run Wiro AI models, build and run workflows, and talk to Studio and your Wiro agents.

1 225 installs/wk answering
Algernon MCP
by sammyboi81

Fan a goal out to cheap parallel LLM workers on your own key or a free local Ollama. Keep your mind.

140 installs/wk local only
Lm
by houtini-ai

Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.

390 installs/wk local only
Ollama Handoff
by michael-whitecapdata

Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.

74 installs/wk local only

Local AI MCP — questions

Answers built from our own checks of this server.

Why is there no uptime for Local AI MCP?
Local AI MCP runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @tmhs/local-ai-mcp was installed 24 times last week.
How do I connect Local AI MCP?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @tmhs/local-ai-mcp straight from npm; nothing to host, nothing to sign up for.
How many people use Local AI MCP?
The npm package @tmhs/local-ai-mcp was installed 24 times in the last week. Week over week that is +80%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Local AI MCP open source?
We cannot say either way: written in TypeScript, 0 stars on GitHub and 2 open issues, but we could not determine the licence, and without one the code is not open source by default.