How to Use the Zeev MCP in Mastra AI

Q: How do I start a new process with Zeev using Mastra AI?

You call the createrequest tool. The MCP Server handles the initiation, allowing your agent to monitor the resulting workflow instance immediately.

Q: Should I use getrequest or listrequests with Mastra AI?

Use listrequests for an overview of all running processes, but if you have a specific ID, call getrequest. It gives you the deep details needed for your agent.

Q: Can I check who needs to finish a task using the Mastra AI MCP Server?

Absolutely. You can use listtasks or gettask to identify pending work, which allows your agent to then delegate it if necessary.

Build robust, failure-proof workflows using Mastra AI with Zeev.

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 Mastra AI

Create your Vinkius account to connect Zeev to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control the Workflow Lifecycle

The `create_request` tool lets you initiate any process defined in Zeev. Since your agent framework handles retries and failure, you can build workflows that automatically restart or branch when a step fails. You manage the full lifecycle using tools like `get_task`, `finish_task`, and `cancel_request`. It’s built for reliable, multi-step operations.

Inspect Process Definitions

To get started, you first need to know what's possible. Use `list_processes` to see all available Zeev workflows. Then, call `get_process` to pull the full definition—the exact blueprint your agent needs. This setup ensures that complex logic only runs against validated process structures.

Manage User and Task Status

You can always verify who's running what. `get_me` provides current user details, while `list_tasks` gives a list of pending work items. If the task is assigned to someone else, you use `delegate_task`. It keeps your complex agent workflows accountable and auditable.

Setup guide

Set up Zeev MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Zeev tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "zeev-mcp-client",
  servers: {
    "zeev-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Zeev Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Zeev tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Zeev transactions"
);
console.log(result.text);

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 Mastra AI

You call the `create_request` tool. The MCP Server handles the initiation, allowing your agent to monitor the resulting workflow instance immediately.

The combination is built for reliability. Your agent framework manages retries and conditional branching, ensuring that failures in a process request don't stop the whole operation.

Use `list_requests` for an overview of all running processes, but if you have a specific ID, call `get_request`. It gives you the deep details needed for your agent.

The primary data type handled is 'Process Request' and 'Task'. Your workflow deals with the status and definition of these items.

Absolutely. You can use `list_tasks` or `get_task` to identify pending work, which allows your agent to then delegate it if necessary.

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