How to Use the Zeev MCP in Vercel AI SDK

Q: Can the Vercel AI SDK help me find my user info for Zeev tasks?

Yes. You can use getme to fetch current user information before performing actions like delegating a task or starting an approval process via the MCP Server.

Q: If I need to know about a specific workflow, which tool should I use with the Vercel AI SDK?

Use getrequest if you have the instance ID, or check out listrequests first. The MCP Server provides detailed process status updates for your agent.

Stream real-time process data into your 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 Zeev MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Process Requests

When you call `create_request`, you immediately kick off a workflow instance in Zeev. This tool lets you start complex, multi-step business processes—think automated approval chains or digitized forms—right from your React frontend. You get real-time visibility into the whole thing. You can track status changes and check details using `get_request` as soon as the process is running.

Handle Tasks and Approvals

Got a pending review? Use `delegate_task` to hand off work to another user, or trigger immediate action with `finish_task`. These tools treat Zeev workflows like actual business operations, not just database entries. If something goes sideways, you can stop the whole thing by calling `cancel_request`, preventing bad data from getting submitted.

List and Inspect Workflows

Need to know what systems are available? The `list_processes` tool shows every defined BPMN workflow in Zeev. You can then pull specific definitions using `get_process`, which gives you the blueprint for how a process runs. Want an overview of everything running? Just run `list_requests` or check out pending items with `list_tasks`. It's all available to your AI client.

Setup guide

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

The MCP Server connects directly, allowing your agent to call any Zeev function in real-time. You'll see data pop into your UI as it changes, bypassing standard loading spinners.

Zeev handles anything that replaces paper chaos. This means automated approval chains, complex forms, or any multi-step business workflow that needs tracking.

Yes. You can use `get_me` to fetch current user information before performing actions like delegating a task or starting an approval process via the MCP Server.

Use `get_request` if you have the instance ID, or check out `list_requests` first. The MCP Server provides detailed process status updates for your agent.

This server touches 'Process Request' and 'User Information'. Your agent manages the lifecycle of these specific business workflows.

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