4,000+ servers built on vurb.ts
Vinkius

LocalAI MCP Server for Mastra AIGive Mastra AI instant access to 19 tools to Anthropic Messages, Apply Model, Chat Completions, and more

MCP Inspector GDPR Free for Subscribers

Mastra AI is a TypeScript-native agent framework built for modern web stacks. Connect LocalAI through Vinkius and Mastra agents discover all tools automatically. type-safe, streaming-ready, and deployable anywhere Node.js runs.

Ask AI about this MCP Server for Mastra AI

The LocalAI MCP Server for Mastra AI is a standout in the Ai Frontier category — giving your AI agent 19 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
typescript
import { Agent } from "@mastra/core/agent";
import { createMCPClient } from "@mastra/mcp";
import { openai } from "@ai-sdk/openai";

async function main() {
  // Your Vinkius token. get it at cloud.vinkius.com
  const mcpClient = await createMCPClient({
    servers: {
      "localai": {
        url: "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
      },
    },
  });

  const tools = await mcpClient.getTools();
  const agent = new Agent({
    name: "LocalAI Agent",
    instructions:
      "You help users interact with LocalAI " +
      "using 19 tools.",
    model: openai("gpt-4o"),
    tools,
  });

  const result = await agent.generate(
    "What can I do with LocalAI?"
  );
  console.log(result.text);
}

main();
LocalAI
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About LocalAI MCP Server

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

Mastra's agent abstraction provides a clean separation between LLM logic and LocalAI tool infrastructure. Connect 19 tools through Vinkius and use Mastra's built-in workflow engine to chain tool calls with conditional logic, retries, and parallel execution. deployable to any Node.js host in one command.

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.

The LocalAI MCP Server exposes 19 tools through the Vinkius. Connect it to Mastra AI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 19 LocalAI tools available for Mastra AI

When Mastra AI connects to LocalAI through Vinkius, your AI agent gets direct access to every tool listed below — spanning self-hosted, llm-inference, image-generation, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

anthropic

Anthropic messages on LocalAI

Generate messages (Anthropic compatible)

apply

Apply model on LocalAI

Install a model from the gallery

chat

Chat completions on LocalAI

Generate chat completions (OpenAI compatible)

create

Create embeddings on LocalAI

Create text embeddings

detect

Detect objects on LocalAI

Detect objects in an image

face

Face analyze on LocalAI

Analyze face demographics

face

Face identify on LocalAI

Identify faces (1:N)

face

Face register on LocalAI

Enroll a face into the store

face

Face verify on LocalAI

Verify faces (1:1)

generate

Generate image on LocalAI

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

get

Get auth status on LocalAI

Check authentication state and providers

get

Get auth usage on LocalAI

View personal token usage

get

Get system info on LocalAI

View system and backend info

get

Get version on LocalAI

Get LocalAI version

list

List models on LocalAI

List available models

open

Open responses on LocalAI

Generate open responses

rerank

Rerank documents on LocalAI

Rerank documents based on a query

text

Text to speech on LocalAI

Convert text to audio (TTS)

transcribe

Transcribe audio on LocalAI

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

Connect LocalAI to Mastra AI via MCP

Follow these steps to wire LocalAI into Mastra AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install dependencies

Run npm install @mastra/core @mastra/mcp @ai-sdk/openai
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token
03

Run the agent

Save to agent.ts and run with npx tsx agent.ts
04

Explore tools

Mastra discovers 19 tools from LocalAI via MCP

Why Use Mastra AI with the LocalAI MCP Server

Mastra AI provides unique advantages when paired with LocalAI through the Model Context Protocol.

01

Mastra's agent abstraction provides a clean separation between LLM logic and tool infrastructure. add LocalAI without touching business code

02

Built-in workflow engine chains MCP tool calls with conditional logic, retries, and parallel execution for complex automation

03

TypeScript-native: full type inference for every LocalAI tool response with IDE autocomplete and compile-time checks

04

One-command deployment to any Node.js host. Vercel, Railway, Fly.io, or your own infrastructure

LocalAI + Mastra AI Use Cases

Practical scenarios where Mastra AI combined with the LocalAI MCP Server delivers measurable value.

01

Automated workflows: build multi-step agents that query LocalAI, process results, and trigger downstream actions in a typed pipeline

02

SaaS integrations: embed LocalAI as a first-class tool in your product's AI features with Mastra's clean agent API

03

Background jobs: schedule Mastra agents to query LocalAI on a cron and store results in your database automatically

04

Multi-agent systems: create specialist agents that collaborate using LocalAI tools alongside other MCP servers

Example Prompts for LocalAI in Mastra AI

Ready-to-use prompts you can give your Mastra AI agent to start working with LocalAI immediately.

01

"List all models available on my LocalAI instance."

02

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

03

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

Troubleshooting LocalAI MCP Server with Mastra AI

Common issues when connecting LocalAI to Mastra AI through Vinkius, and how to resolve them.

01

createMCPClient not exported

Install: npm install @mastra/mcp

LocalAI + Mastra AI FAQ

Common questions about integrating LocalAI MCP Server with Mastra AI.

01

How does Mastra AI connect to MCP servers?

Create an MCPClient with the server URL and pass it to your agent. Mastra discovers all tools and makes them available with full TypeScript types.
02

Can Mastra agents use tools from multiple servers?

Yes. Pass multiple MCP clients to the agent constructor. Mastra merges all tool schemas and the agent can call any tool from any server.
03

Does Mastra support workflow orchestration?

Yes. Mastra has a built-in workflow engine that lets you chain MCP tool calls with branching logic, error handling, and parallel execution.

Explore More MCP Servers

View all →