How to Use the Zesty.io MCP in Vercel AI SDK

Q: If I need to check multiple Zesty.io instances in Vercel AI SDK, what tool should I use?

Use listzestyinstances. This function helps your agent identify every associated instance ID, letting you target the correct source for content management operations.

Q: Does Zesty.io support deleting items via Vercel AI SDK?

Yes. You can use deletecontentitem to remove specific data records. This is a simple, direct action that your streamed response confirms immediately.

Stream content changes live into 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 Zesty.io MCP to Vercel AI SDK

Create your Vinkius account to connect Zesty.io 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 Zesty.io with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time Content Retrieval

Need to display content details instantly? Use `get_content_item` to fetch specific data points from Zesty.io and stream the result directly into your React or Svelte component. This makes the user experience feel live, bypassing standard loading spinners. If you need a list of items instead, call `list_content_items`. The resulting array streams in real-time, allowing users to see content populate as it arrives on the client side.

Live Content Creation

Building a form that writes data? Call `create_content_item` and stream the successful operation confirmation back to the user's view. Your agent handles the JSON payload, and your UI gets immediate feedback. Want to change something already there? Use `update_content_item`. Streaming this update confirms to the end-user that their action worked instantly.

Managing Content Schemas

First, identify what data you're working with. Running `list_content_models` gives your agent the Model ZUIDs it needs for subsequent calls. This tool tells you exactly how to structure your future content items. Need to check system limits? Call `get_instance_settings`. The configuration details stream right into your code, letting you validate settings before running any write operation.

Setup guide

Set up Zesty.io 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 Zesty.io 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 Zesty.io 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 Zesty.io. 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 Zesty.io 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 Zesty.io MCP in Vercel AI SDK

The results from the MCP Server stream directly into your front-end framework (React, Next.js, etc.). You don't wait for a final JSON blob; you see the data appear live as it streams through the client.

The server lets your agent list all available content models using `list_content_models`. These models define the structure and fields for every piece of content you create or retrieve.

Use `list_zesty_instances`. This function helps your agent identify every associated instance ID, letting you target the correct source for content management operations.

Yes. You can use `delete_content_item` to remove specific data records. This is a simple, direct action that your streamed response confirms immediately.

This server primarily handles structured content data and instance configuration settings. You interact with model-defined fields, item records, and API parameters.

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