How to Use the zrok (Open-Source Tunnel) MCP in Mastra AI

Q: How does zrok (Open-Source Tunnel) help manage tunnel resources with Mastra AI?

You use tools like listshares to check the current status of all tunnels. This allows your workflow engine to make decisions—if a share exists, it skips creation; otherwise, it calls createshare.

Q: Can I handle environment state changes with zrok (Open-Source Tunnel) and Mastra AI?

Yes. You can use listenvironments, followed by calling either enableenvironment or disableenvironment. This lets your workflow control the underlying network resources needed for a process.

Q: If my complex workflow fails, how does zrok (Open-Source Tunnel) assist with Mastra AI retries?

The agent can use getaccount to check limits and then call loginaccount. This ensures that the credentials are valid before attempting a retry of the failed operation.

Q: What happens if I need to remove temporary tunnels using zrok (Open-Source Tunnel) with Mastra AI?

The agent executes deleteshare. This is critical for cleanup, ensuring that once a complex task finishes, the shared tunnel is immediately terminated and resources are freed up.

Q: What kind of data does zrok (Open-Source Tunnel) touch when registering an account with Mastra AI?

The process involves registeraccount, which captures new account credentials. This is necessary for the workflow to establish a persistent connection and manage subsequent shared resources.

Build reliable, multi-step tunnels with Mastra AI for complex workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect zrok (Open-Source Tunnel) MCP to Mastra AI

Create your Vinkius account to connect zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Tunnel Lifecycle in Workflows

The `zrok (Open-Source Tunnel)` MCP Server lets you manage the entire tunnel lifecycle. A workflow can use `create_share` to spin up a new public resource, and later call `delete_share` once the job is complete. This sequence of actions allows your Mastra AI agent to build robust processes that know exactly when to start and stop sharing resources.

Handle Account Access for Retries

For multi-step workflows, you might need to re-authenticate. The `zrok (Open-Source Tunnel)` tool provides `login_account` so the agent can refresh tokens and retry failed steps. This makes your Mastra AI processes resilient; if an initial connection fails, the workflow automatically re-authenticates before trying again.

Check Resource Availability Before Running

Before a complex task runs, you need to know what's available. Use `list_shares` and `get_share` to check existing tunnels. The agent gathers this data first. It checks if the required share already exists or if it needs to call `create_share`. This prevents unnecessary steps and keeps your complex workflow clean.

Setup guide

Set up zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) 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: "zrok-open-source-tunnel-mcp-client",
  servers: {
    "zrok-open-source-tunnel-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent zrok (Open-Source Tunnel) 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 zrok. 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 zrok (Open-Source Tunnel) 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 zrok (Open-Source Tunnel) MCP in Mastra AI

You use tools like `list_shares` to check the current status of all tunnels. This allows your workflow engine to make decisions—if a share exists, it skips creation; otherwise, it calls `create_share`.

Yes. You can use `list_environments`, followed by calling either `enable_environment` or `disable_environment`. This lets your workflow control the underlying network resources needed for a process.

The agent can use `get_account` to check limits and then call `login_account`. This ensures that the credentials are valid before attempting a retry of the failed operation.

The agent executes `delete_share`. This is critical for cleanup, ensuring that once a complex task finishes, the shared tunnel is immediately terminated and resources are freed up.

The process involves `register_account`, which captures new account credentials. This is necessary for the workflow to establish a persistent connection and manage subsequent shared resources.

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