How to Use the Avochato MCP in Vercel AI SDK

Q: How do I connect the Avochato MCP Server to my Vercel AI SDK project?

Install the required packages with npm install ai @ai-sdk/mcp. Use createMCPClient to point to your Vinkius endpoint, then pass the tools directly into streamText or generateText. Remember to call mcpClient.close() once the execution finishes.

Q: Can I use Avochato webhooks with Vercel AI SDK edge functions?

Yes. You can register endpoints using createwebhook from any Edge Function. Incoming SMS events then trigger your serverless routes to process replies in real time.

Q: Does the Avochato integration with Vercel AI SDK support MMS media files?

Yes. When calling sendmessage, you can pass media URLs alongside your text content. The client handles the payload and delivers the media directly to the recipient's handset.

Q: How does the model handle contact creation with this integration?

The agent checks if a user exists using getcontact or listcontacts. If it finds nothing, it calls createcontact to save the new phone number and name to your database.

Stream real-time SMS updates and customer ticket changes directly into your Next.js UI using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Avochato MCP to Vercel AI SDK

Create your Vinkius account to connect Avochato to Vercel AI SDK 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 Avochato with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live SMS updates in your Vercel AI SDK frontend

Your users don't want to wait for a spinning wheel when sending texts. Connect your app directly to the Avochato API using this MCP Server. When your agent calls `send_message` or `list_messages`, the raw payload streams straight to your React or Next.js components. This setup runs perfectly on Edge Functions. You can fetch contact logs with `get_contact` and update the view instantly. No lag, no unnecessary state management, just pure real-time data flow.

Manage support tickets inside the chat interface

Let your agent handle customer support directly in the chat window. By exposing `list_tickets` and `update_ticket`, your interface can show active support threads and let the model resolve them on the fly. The UI reflects changes the second they happen. If a conversation needs escalation, the agent triggers `update_contact` to flag the user. Your frontend updates without a page reload.

Dynamic webhook routing for developers

Programmatic control over your messaging pipelines shouldn't require manual configuration. This MCP Server lets your application deploy and tear down endpoints dynamically using `create_webhook` and `delete_webhook`. You can monitor active connections with `list_webhooks` to ensure your messaging stack stays healthy. It gives your application complete control over how incoming SMS events route to your server.

Setup guide

Set up Avochato MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Avochato tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Avochato transactions",
});

console.log(text);
await mcpClient.close();

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 Avochato. 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 Avochato 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 Avochato MCP in Vercel AI SDK

Install the required packages with `npm install ai @ai-sdk/mcp`. Use `createMCPClient` to point to your Vinkius endpoint, then pass the tools directly into `streamText` or `generateText`. Remember to call `mcpClient.close()` once the execution finishes.

Yes. You can register endpoints using `create_webhook` from any Edge Function. Incoming SMS events then trigger your serverless routes to process replies in real time.

Yes. When calling `send_message`, you can pass media URLs alongside your text content. The client handles the payload and delivers the media directly to the recipient's handset.

The agent checks if a user exists using `get_contact` or `list_contacts`. If it finds nothing, it calls `create_contact` to save the new phone number and name to your database.

Your SMS payloads, contact records, and webhook secrets never persist on Vinkius. Every MCP tool call runs inside an isolated, ephemeral V8 sandbox that is destroyed immediately after execution.

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