LocalAI

LocalAI MCP Connector for Claude

A+

Run LLMs, generate images, and process audio locally. OpenAI-compatible API for your own hardware.

19 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect your LocalAI instance to any AI agent and leverage powerful multimodal capabilities directly from your own infrastructure.

What you can do

  • Text Generation — Use chat_completions or anthropic_messages to generate text using local models with full OpenAI or Anthropic compatibility.
  • Image Synthesis — Create visual content from text prompts using the generate_image tool, supporting custom sizes and negative prompts.
  • Audio Processing — Convert speech to text with transcribe_audio or generate natural-sounding speech from text using text_to_speech.
  • Advanced Search & RAG — Generate vector embeddings with create_embeddings and improve search relevance using the rerank_documents tool.
  • Computer Vision — Analyze images and identify elements using the detect_objects tool.
  • System Management — Monitor your instance with list_models, get_system, and getVersion to ensure optimal performance.

How it works

  1. Subscribe to this server
  2. Provide your LocalAI Base URL (e.g., http://localhost:8080) and optional API Key
  3. Start interacting with your local models through Claude, Cursor, or any MCP client

Who is this for?

  • Privacy-Conscious Developers — Run powerful AI workflows without sending sensitive data to third-party cloud providers.
  • AI Researchers — Easily test and swap different local models for chat, vision, and audio tasks.
  • DevOps Engineers — Integrate local AI capabilities into internal tools and automated pipelines.
self-hostedllm-inferenceimage-generationaudio-processingopenai-compatiblelocal-models

19 tools expose this connector's capabilities to your AI agent.

anthropic_messages

Generate messages (Anthropic compatible)

apply_model

Install a model from the gallery

chat_completions

Generate chat completions (OpenAI compatible)

create_embeddings

Create text embeddings

detect_objects

Detect objects in an image

face_analyze

Analyze face demographics

face_identify

Identify faces (1:N)

face_register

Enroll a face into the store

face_verify

Verify faces (1:1)

generate_image

Supports negative prompts using | separator. Generate images from text prompts

get_auth_status

Check authentication state and providers

get_auth_usage

View personal token usage

get_system_info

View system and backend info

get_version

Get LocalAI version

list_models

List available models

open_responses

Generate open responses

rerank_documents

Rerank documents based on a query

text_to_speech

Convert text to audio (TTS)

transcribe_audio

Pass the file data or path as required by your LocalAI setup. Transcribe audio to text

See how to talk to your AI agent using LocalAI.

List all models available on my LocalAI instance.

I've retrieved the list of models. You have 'llama-3-8b', 'stablediffusion', and 'whisper-1' currently active and ready for use.

Generate a chat response using the 'llama-3' model about the benefits of local AI.

Using the 'llama-3' model: Local AI offers significant benefits including enhanced data privacy, reduced latency, and the ability to operate without an internet connection...

Create an image of a futuristic library using the 'stablediffusion' model.

I've initiated the image generation for a 'futuristic library'. The process is complete, and you can view the generated image at the provided local URL.

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

Related Connectors