How to Use the LocalAI MCP in Claude

Q: How do I connect LocalAI to Claude Desktop?

Open your claudedesktopconfig.json file and add the server under the mcpServers key. Point the command to your node installation to activate the MCP Server, then restart Claude Desktop to load the tools.

Q: Can I use LocalAI to run embeddings in Claude Desktop?

Yes. This server exposes createembeddings directly to your agent, allowing Claude Desktop to index and search your local documents without sending any text to external servers.

Run private LLMs and voice-to-text models directly from your Claude Desktop app using your own hardware.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LocalAI MCP to Claude Desktop

Create your Vinkius account to connect LocalAI to Claude Desktop and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup LocalAI with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate images and detect objects inside Claude Desktop

The `detect_objects` and `face_analyze` tools let Claude Desktop process images directly on your local machine. This MCP Server lets you analyze physical objects and facial attributes inside your desktop chat window without your files ever leaving your local drive. Need to build visual assets on the fly? Run `generate_image` to spin up graphics using your local GPU right inside the chat window. The server handles complex prompt structures and negative prompts behind the scenes, outputting files directly to your workspace.

Run local speech-to-text and chat completions

Running `transcribe_audio` and `text_to_speech` lets Claude Desktop handle audio files locally without hitting external cloud APIs. Your desktop agent processes audio payloads on your machine, giving you quick turnarounds for meeting notes or voice synthesis right in your chat. You can also swap backends on the fly. The server uses `chat_completions` and `list_models` to check what open-source models are running on your local rig, letting your agent route text work to the most efficient local model available.

Install models directly from Claude Desktop

The `apply_model` tool lets Claude Desktop manage your local model catalog, turning your local system into an active MCP Server. This removes the need to jump back and forth to your terminal just to download and configure new models from the local gallery. Keep tabs on your hardware resources without leaving your workflow. The `get_system_info` tool lets your agent monitor local VRAM and CPU usage so you don't crash your machine when running heavy inference tasks.

Setup guide

Set up LocalAI MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The LocalAI MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the LocalAI MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under localai-mcp.

json

{
  "mcpServers": {
    "localai-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by LocalAI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect LocalAI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about LocalAI MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the server under the `mcpServers` key. Point the command to your node installation to activate the MCP Server, then restart Claude Desktop to load the tools.

Yes. This server exposes `create_embeddings` directly to your agent, allowing Claude Desktop to index and search your local documents without sending any text to external servers.

This usually happens when the model names in your configuration don't match what is installed. Have your agent run `list_models` to check which weights are active on your local instance and adjust your prompts accordingly.

It depends entirely on your GPU. While light text tasks like `open_responses` run quickly on modern chips, heavy visual tasks like `face_identify` require dedicated VRAM to avoid dragging down your system.

Your local audio recordings and images never leave your computer. The MCP server processes them entirely in memory on your physical hardware, meaning no external company can store, view, or train on your private media.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript