How to Use the LocalAI MCP in Claude Code

Connect Claude Code to your local AI hardware for headless, private automation.

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 Code

Create your Vinkius account to connect LocalAI to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless automation with Claude Code

Use this MCP Server in your CI/CD pipelines to run inference locally. Call `chat_completions` or `create_embeddings` from your shell scripts to verify builds. It removes the need for expensive API calls during routine checks. You get the same output quality while keeping your infrastructure costs predictable.

System info and monitoring

Get real-time feedback on your model performance using `get_system_info` and `get_version`. You can script these checks to monitor your GPU load. It gives you the data you need to adjust your pipelines. If a model starts lagging, your scripts can catch it immediately.

Batch processing with Claude Code

Run mass transcriptions or text-to-speech tasks using your terminal. Pipe your file paths to `transcribe_audio` to automate your documentation workflows. It handles the data stream without human intervention. You can chain these commands in a cron job to keep your files processed automatically.

Setup guide

Set up LocalAI MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see localai-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest LocalAI transactions." It will automatically discover and invoke the available LocalAI tools.

Terminal

claude mcp add --transport http localai-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the LocalAI MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "localai-mcp": {
      "type": "url",
      "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 Code

Yes. You connect the server via the CLI using the add command. It runs as a headless process, perfect for terminal-based workflows.

It is. You can use it to run automated tests and document processing in your GitHub Actions or local shell environments.

Run the command 'claude mcp add --transport http -- ' in your terminal. This registers the server, allowing your scripts to call the tools.

The connection is restricted to your localhost. No data travels over the public internet, ensuring your sensitive pipeline logs remain completely private.

It does. After you add the server, you can list the available tools to verify they are ready for your scripts. The server exposes everything through the standard MCP interface.

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