How to Use the Zixflow MCP in Vercel AI SDK

Q: How do I search Zixflow data using the Vercel AI SDK?

You invoke listcollectionrecords, passing a JSON body that filters your search. The results stream back to the client in real time, letting you display specific contact or company details immediately.

Q: Does the Vercel AI SDK handle authentication for Zixflow?

Yes, you can use the built-in authProvider to manage OAuth tokens. This keeps your endpoint secure while allowing your agent client access to the necessary tools.

Q: If I change a record with Zixflow and Vercel AI SDK, how is it confirmed?

The updatecollectionrecord tool sends confirmation data that streams back. This direct feedback lets you tell the user exactly when the save operation finished.

See Zixflow data appear in real time using 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 Zixflow MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Zixflow Data with the MCP Server

The `list_collection_records` tool lets your agent pull a full list of records from any specific collection. Because you're using Vercel AI SDK, this data streams directly into your UI as it arrives—no loading spinners required. This real-time flow means users see the results instantly. Build user-facing products that actually feel fast; the AI work happens live in the browser.

Updating Records via Vercel AI SDK

Need to change a contact's phone number or update a company record? Just call `update_collection_record`. Your agent sends the necessary changes, and you get confirmation back immediately. This makes building stateful forms really simple. Whether you use it for lead qualification or post-sale follow-up, modifying data is straightforward. The Vercel AI SDK handles this update result just like any other streamed tool output.

Listing All Sales Collections with the MCP Server

Before you write code to pull data, you need to know what collections exist. `list_collections` gives a master list (People, Company, etc.). This is critical for building smart selectors that guide your user through the process. It's simple setup: get the list, show it to the user, and then let them pick where they want to run their next query. The Vercel AI SDK makes this whole interaction feel native.

Setup guide

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

You invoke `list_collection_records`, passing a JSON body that filters your search. The results stream back to the client in real time, letting you display specific contact or company details immediately.

You manage sales contacts, full company records, and transaction history. The MCP Server supports reading and writing these various types of core business intelligence.

Yes, you can use the built-in `authProvider` to manage OAuth tokens. This keeps your endpoint secure while allowing your agent client access to the necessary tools.

The `update_collection_record` tool sends confirmation data that streams back. This direct feedback lets you tell the user exactly when the save operation finished.

The MCP Server handles 'contact records and transactions' data. All interactions require an endpoint token, ensuring that your agent client only accesses what you explicitly allow.

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