How to Use the LocalAI MCP in Windsurf

Q: How do I add the LocalAI MCP Server to Windsurf?

Open your mcpconfig.json file or use the Cascade settings panel. Add the server details under the mcpServers key, then click refresh to see the tools.

Run local LLMs and image models inside Windsurf to keep your data private and your workflow fast.

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 Windsurf

Create your Vinkius account to connect LocalAI to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Local model orchestration in Windsurf

Cascade uses this MCP Server to manage your local hardware directly. You can trigger `chat_completions` or `list_models` without sending a single byte to a cloud provider. Your agent handles model selection based on your available VRAM. It pulls from your local gallery to ensure the IDE stays fast even when you are offline.

Generate assets with Windsurf

Create images or audio files without leaving your editor. Use `generate_image` with specific negative prompts to control output quality directly from your chat context. Everything stays on your machine. You get the file locally the moment it finishes processing, keeping your creative flow uninterrupted by network latency.

Process media locally

Transcribe recordings or convert text to voice using `transcribe_audio` and `text_to_speech`. This server handles the heavy lifting so Windsurf stays responsive. Feed your audio paths directly into the tool. The server returns the text or audio file to your workspace instantly.

Setup guide

Set up LocalAI MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my LocalAI payment history." If connected, Cascade will call the LocalAI tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Yes. This server connects your local instance to the IDE, ensuring all model inference stays on your machine. Your code never leaves your local environment.

Absolutely. You can call the image tools directly through the Cascade interface. It uses your local GPU to render the files.

Open your mcp_config.json file or use the Cascade settings panel. Add the server details under the mcpServers key, then click refresh to see the tools.

Your data is isolated on your hardware. No external APIs touch your files because the server operates entirely within your local network.

It does. You provide the file path, and the server processes the audio using your local models, keeping the raw data out of any third-party cloud.

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