An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect LocalAI to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Run powerful multimodal AI on your own hardware.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 19 capabilities

We ship only the actions that matter.

Capability set01 / 05

01-04

4 capabilities in this set.

Part of 19 available through LocalAI.

  1. 01

    Detect objects

    Use this to identify and locate specific objects within an image.

  2. 02

    Rerank documents

    Improve search results by reranking documents based on a specific query.

  3. 03

    Chat completions

    This capability provides OpenAI-compatible chat completions for your local models.

  4. 04

    Create embeddings

    Generate text embeddings for use in search or RAG workflows.

Capability set02 / 05

05-08

4 capabilities in this set.

Part of 19 available through LocalAI.

  1. 05

    Face analyze

    Analyze faces to determine demographic information.

  2. 06

    Face register

    Enroll a new face into your local identity store.

  3. 07

    Face verify

    This capability performs 1:1 face verification to confirm an identity.

  4. 08

    Generate image

    Create new images from text prompts, including support for negative prompts.

Capability set03 / 05

09-12

4 capabilities in this set.

Part of 19 available through LocalAI.

  1. 09

    Get auth status

    Check your current authentication state and available providers.

  2. 10

    Get auth usage

    View your personal token usage for the instance.

  3. 11

    Get system info

    Check your backend and system status to monitor performance.

  4. 12

    Get version

    Retrieve the current version of your LocalAI instance.

Capability set04 / 05

13-16

4 capabilities in this set.

Part of 19 available through LocalAI.

  1. 13

    List models

    Get a list of all models currently available on your local hardware.

  2. 14

    Text to speech

    Convert written text into spoken audio.

  3. 15

    Transcribe audio

    Turn audio files into text using your local transcription models.

  4. 16

    Anthropic messages

    This capability generates messages using Anthropic-compatible formatting for your local models.

Capability set05 / 05

17-19

3 capabilities in this set.

Part of 19 available through LocalAI.

  1. 17

    Open responses

    Generate open-ended responses using your local models.

  2. 18

    Apply model

    Install a new model directly from the gallery to your instance.

  3. 19

    Face identify

    Perform 1:N face identification to find a person in a group.

Real work

What teams actually run

01

Private Document Analysis

Use local embeddings and reranking to query sensitive documents without cloud uploads.

02

Local Content Creation

Generate images and text locally to avoid per-token cloud costs.

03

Automated Audio Transcription

Process large batches of audio files into text using local transcription models.

04

Secure Face Identification

Run face registration and identification tasks on your own local infrastructure.

Automate a task

Put LocalAI to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

LocalAI works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put LocalAI to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

1009ms average. Fast in production.

LocalAI is checked daily against the live service.

Daily averagePeak 1174ms
Oct 3Today
Fastest day
782ms
Slowest day
1174ms
14-day trend
Improving-7%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 19 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of LocalAI, so you can see the experience inside your AI.

It does not authenticate your account with LocalAI. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

LocalAI Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_rNQOAeEr0Jny5r5Ag0JD5dh4JLxiMfgFSBUDjX1k/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — LocalAI capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "localai-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_rNQOAeEr0Jny5r5Ag0JD5dh4JLxiMfgFSBUDjX1k/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up LocalAI in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work LocalAI owners hand off.

This MCP is built for professionals who need to run AI workloads without sending data to the cloud.

  • 01

    Privacy-Conscious Developers

    They hand off sensitive code and data tasks to local models to keep everything on-premise.

  • 02

    AI Researchers

    They use the capability to quickly swap and test different local models for specific tasks.

  • 03

    DevOps Engineers

    They integrate local inference into automated internal pipelines and capabilities.

FAQ

Questions LocalAI owners ask.

  • 01

    How do I connect my local models to Claude?

    You provide your LocalAI Base URL to the MCP, and it acts as the bridge between your local hardware and the Claude client.

  • 02

    Does this work with OpenAI-style code?

    Yes, this MCP provides capabilities that are compatible with OpenAI and Anthropic API structures.

  • 03

    Can I run image generation locally?

    Yes, you can use the generate_image capability to create images from text prompts on your own machine.

  • 04

    Is my data sent to the cloud?

    No, the purpose of this MCP is to allow your AI client to interact with models running on your own local infrastructure.

  • 05

    What models can I use?

    You can use any models you have installed on your LocalAI instance, such as Llama or Stable Diffusion.

  • 06

    How can I see which AI models are currently installed on my LocalAI server?

    You can use the list_models capability. It will return a complete list of all available models on your instance, including their IDs and capabilities.

  • 07

    Does this server support generating images locally?

    Yes! By using the generate_image capability, you can provide a prompt and optional size to generate images directly on your hardware using supported models like Stable Diffusion.

  • 08

    Can I use this to transcribe audio files into text?

    Absolutely. The transcribe_audio capability allows you to send audio data or file paths to your LocalAI instance for high-quality transcription using models like Whisper.

Explore

More in AI Frontier

Suggestions

Connect LocalAI to Claude, Cursor, ChatGPT & more