How to Use the LocalAI MCP in VS Code Copilot

Q: How do we deploy LocalAI for our team in VS Code Copilot?

Create a .vscode/mcp.json file and commit it to your repository. This ensures that every developer using VS Code Copilot automatically connects to the designated MCP Server when they open the project.

Q: Can we run semantic search with LocalAI in VS Code Copilot?

Yes. The MCP server exposes createembeddings and rerankdocuments to Copilot, letting your team perform deep semantic searches through your documentation and code repositories locally.

Q: How do we check the version of our local setup in VS Code Copilot?

You can ask Copilot to run getversion or getsysteminfo to check the active version of your backend and verify that your hardware is properly configured.

Share private local AI models and audio transcription tools across your team directly within VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect LocalAI to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run local completions in VS Code Copilot

The `chat_completions` tool lets VS Code Copilot run code generation tasks pointing directly to your team's local hardware cluster. This MCP Server routes requests to your own infrastructure, standardizing your team's development environment inside VS Code without leaking code to external APIs. By committing a shared configuration to your repository, every developer gets instant access to the same local models. Use `list_models` to verify that everyone on the team is running the exact same model versions for consistent code outputs.

Process voice inputs directly inside your editor

Running `transcribe_audio` directly inside VS Code Copilot lets developers convert spoken notes into markdown files on their own machines. Dictate code comments or generate spoken documentation without sending audio files outside of your VS Code workspace. You can also convert written documentation back into audio files. The `text_to_speech` tool allows your agent to generate audio assets locally, which is perfect for testing accessibility features in your web apps.

Test face verification and object detection locally

The `face_register` and `face_verify` tools let your VS Code Copilot agent test local identity verification pipelines directly from your workspace. This MCP connection runs entirely in your local environment, making it easy to build and debug computer vision applications without paying for expensive cloud APIs. Your agent can write accurate test assertions based on the actual objects detected in your local files. When working on media applications, use `detect_objects` to analyze images in your assets folder.

Setup guide

Set up LocalAI MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the LocalAI MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the LocalAI tools listed. Try asking: "List my recent LocalAI transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a `.vscode/mcp.json` file and commit it to your repository. This ensures that every developer using VS Code Copilot automatically connects to the designated MCP Server when they open the project.

Yes. The MCP server exposes `create_embeddings` and `rerank_documents` to Copilot, letting your team perform deep semantic searches through your documentation and code repositories locally.

Make sure your local instance has internet access to fetch new weights when calling `apply_model`. If you are in an air-gapped environment, you must pre-load the models onto your local disk.

You can ask Copilot to run `get_version` or `get_system_info` to check the active version of your backend and verify that your hardware is properly configured.

Your source code files, text queries, and model weights are kept entirely within your local network. No code is transmitted to external servers, satisfying strict enterprise data compliance policies.

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