How to Use the Toket MCP in Vercel AI SDK

Q: How do I handle Toket transactions with Vercel AI SDK?

You call the necessary tool—like mintnft or getgastankstatus—and stream the result. Your AI client handles the crypto details, giving you real-time access to the transaction outcome right in your UI.

Q: Does using Toket with Vercel AI SDK affect my Edge Function?

No. The ai-sdk is designed for Edge Functions. Since it handles streaming data efficiently, calling the MCP Server tools won't bottleneck your function and keeps your UI fast.

Build live NFT tools in your 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 Toket MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Listing Data and Collections

When a user needs to see all available NFTs, the agent runs `list_collections` or `list_mints`. Instead of waiting for one big chunk of data, your AI client streams results directly into the React component. This makes the experience feel instant—the list appears piece by piece as it’s processed. You can use this streaming capability to build a dashboard that updates in real-time, showing everything from `get_gas_tank_status` checks to displaying all active collections.

Monitor Minting Status Live

Minting NFTs involves waiting for confirmations. By calling `mint_nft`, the agent initiates the transaction, and you can follow up immediately with `get_mint_status`. Streaming allows your UI to show progress bars or status changes as they arrive. This real-time feedback is critical for a good user experience. Users hate watching spinners; showing data appear live makes your product feel fast and polished.

Handle Simple NFT Creation

Need to set up a new collection? Your agent executes `create_collection` using simple inputs like name, symbol, and owner wallet. The result streams back immediately, confirming the setup in your UI. If you want to check details later, simply calling `get_collection` returns data that can be streamed into an info panel alongside other live updates.

Setup guide

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

You call the necessary tool—like `mint_nft` or `get_gas_tank_status`—and stream the result. Your AI client handles the crypto details, giving you real-time access to the transaction outcome right in your UI.

The MCP Server exposes NFT metadata, gas tank status, collection lists (`list_collections`), and minting transaction statuses. All this structured data streams directly to your frontend.

Yes. You can build a checkout widget that uses the MCP Server to process payment checks and NFT creation calls, ensuring the user sees every step happening live on their screen.

No. The `ai-sdk` is designed for Edge Functions. Since it handles streaming data efficiently, calling the MCP Server tools won't bottleneck your function and keeps your UI fast.

This server primarily touches NFT metadata, collection names, minting transaction hashes, owner wallet addresses, and gas tank balances. It's all structured crypto-related 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