How to Use the Afosto MCP in Mastra AI

Q: How do I add the Afosto tools to my Mastra AI agent?

After npm install @mastra/mcp@latest, you instantiate the MCPClient with your Vinkius server URL. Then just call mcpClient.listTools() and spread the result into your agent's tool configuration.

Build reliable, multi-step e-commerce workflows. Automate your Afosto operations with Mastra AI's conditional logic and automatic retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Afosto MCP to Mastra AI

Create your Vinkius account to connect Afosto to Mastra AI 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 Afosto with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Your Order Fulfillment Logic

Stop manually checking orders. A Mastra AI agent can use `list_orders` to get new sales, then immediately call `list_inventory` to confirm stock. This simple check prevents you from selling items you don't have. Here’s the key: Mastra's workflow engine lets you add conditional logic. If stock is low, the agent can automatically trigger a different process, like sending a Slack alert or creating a purchase order. If a network call fails, automatic retries with backoff mean your workflow doesn't just crash.

Build Resilient Data Sync Jobs

Syncing data between systems is always brittle. With Mastra AI, you can build an agent that's designed to handle failure. For example, set up a recurring job that uses `list_customers` to pull new profiles from Afosto and push them to your CRM. If your CRM's API is down, a typical script would fail. A Mastra AI agent, however, will automatically retry the operation. This makes your backend integrations far more robust without you having to write a bunch of boilerplate error-handling code.

Create Smart Inventory Alerts with an MCP Server

Don't wait for a stockout to realize you're out of inventory. You can deploy a Mastra AI agent that periodically runs `list_inventory` to check levels across all your warehouses. It's a simple, powerful monitoring tool. Because Mastra AI supports branching, the agent can do more than just send an alert. It can decide *what* to do. If stock for a popular item from `list_products` is low but not critical, it might send an email. If it's critical, it can page the warehouse manager directly.

Setup guide

Set up Afosto MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Afosto tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "afosto-mcp-client",
  servers: {
    "afosto-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Afosto Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Afosto tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Afosto transactions"
);
console.log(result.text);

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 Afosto. 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 Afosto 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 Afosto MCP in Mastra AI

After `npm install @mastra/mcp@latest`, you instantiate the `MCPClient` with your Vinkius server URL. Then just call `mcpClient.listTools()` and spread the result into your agent's tool configuration.

Mastra AI is built for this. It has automatic retries with exponential backoff, so it will try to connect again without you needing to intervene. Your workflows are much more likely to complete successfully.

Yes. Mastra AI supports human-in-the-loop workflows. You can use the `requireToolApproval` option to make the agent pause and wait for a person to confirm a step before it proceeds.

That's a perfect use case. You can create a multi-step workflow where the agent gets an order, calls `list_inventory` to check stock, and only proceeds if the items are available. If not, it can branch to a different task, like notifying the customer.

No. The MCP server operates on a zero-trust model inside a V8 sandbox. Your Afosto inventory and product data passes through but is never stored. Each request is authenticated by your token and the data is gone once the job is done.

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