How to Use the Towio MCP in Vercel AI SDK

Q: How do I check Towio API connectivity using Vercel AI SDK?

Just call getapiversion. The result streams back, confirming the current operational status of your MCP Server connection. This is a quick way to validate that your endpoint token and transport layer are working correctly.

Q: What data type does Towio handle for listing documents?

The listdeliverydocuments tool deals specifically with delivery document records. When your agent client runs this, it streams back a list of available document identifiers and associated metadata.

Q: Can I manage multiple Towio projects with Vercel AI SDK?

Absolutely. You can call listprojects to get all project IDs first. Then, you'll use those IDs in subsequent calls to fetch specific details for each one through the streaming interface.

Q: How do I get all pending tasks from Towio with Vercel AI SDK?

You use the listtasks tool. The streaming nature means you see every task record pop up as it's processed, which is better than waiting for a single massive array of data.

See Towio operations data stream live into your React UI with 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 Towio MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Live Status Updates via MCP Server

When you call `list_tasks`, the results stream instantly to your frontend. This means users see job status changes—like a tow truck arriving or a task being marked complete—as they happen, without waiting for a full page refresh. The Vercel AI SDK handles this streaming behavior natively. You get real-time data updates from Towio's MCP Server, making your application feel live and responsive to the user.

Build Employee Directories in Real Time

Need a list of personnel? Using `list_employees` pushes company employee records directly into your UI stream. Your agent client pulls this data, and you can display it live as the response arrives. This real-time feedback is perfect for building internal tools where users need to see directory information pop up immediately after querying Towio's system.

View Operational Projects on Demand

The `list_projects` tool pulls all active towio projects. Because we're streaming, you don't get a massive JSON blob at the end; you see project names and summaries appearing sequentially in your React component. This is crucial for user-facing applications. You can show progress to the user as the data stream fills up, dramatically improving perceived performance.

Setup guide

Set up Towio 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 Towio 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 Towio 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 Towio. 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 Towio 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 Towio MCP in Vercel AI SDK

Just call `get_api_version`. The result streams back, confirming the current operational status of your MCP Server connection. This is a quick way to validate that your endpoint token and transport layer are working correctly.

The `list_delivery_documents` tool deals specifically with delivery document records. When your agent client runs this, it streams back a list of available document identifiers and associated metadata.

Absolutely. You can call `list_projects` to get all project IDs first. Then, you'll use those IDs in subsequent calls to fetch specific details for each one through the streaming interface.

The stream will fail early. Your agent client should catch this failure gracefully, allowing you to display a specific 'Authentication Failed' message in the UI instead of just showing a loading spinner.

You use the `list_tasks` tool. The streaming nature means you see every task record pop up as it's processed, which is better than waiting for a single massive array of data.

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