How to Use the ngrok MCP in Mastra AI

Q: How do I initialize the ngrok MCP Server in Mastra AI?

Install @mastra/mcp@latest. Create a new MCPClient instance and pass the Vinkius URL into the servers object. Mastra auto-detects whether to use SSE or Streamable HTTP.

Q: Can Mastra AI require human approval for ngrok audits?

Yes. You can configure requireToolApproval on the agent. When the workflow attempts to run listippolicies, it pauses execution until an admin clicks approve.

Q: How do I pass the tools to my agent?

Call mcpClient.listTools() and spread the result into your agent's tool array. The workflow will immediately understand how to query endpoints and vaults.

Build resilient workflows in Mastra AI to monitor and audit your ngrok infrastructure automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ngrok MCP to Mastra AI

Create your Vinkius account to connect ngrok 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 ngrok with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map network edges with Mastra AI

Manual tunnel tracking breaks down at scale. You drop this MCP Server into your Mastra AI workflow to build an automated discovery loop. The agent runs `list_https_edges` on a schedule, mapping every public-facing URL your team created. Conditional branching makes this powerful. If the agent finds a new edge, it checks the rules via `list_ip_restrictions`. When a tunnel lacks the right IP whitelist, Mastra routes the workflow to an alert node, sending a Slack message to the security channel before retrying the check an hour later.

Track API keys across accounts

Developers leave test keys active constantly. Your agent can execute `list_api_keys` to pull the current inventory of ngrok credentials. Mastra takes that JSON array and compares it against your internal developer database. Mastra handles the API failures for you. If the ngrok endpoint times out, the built-in exponential backoff automatically retries the tool call. You get a reliable audit of your keys without writing custom retry logic for the MCP client.

Build reliable endpoint checks

Tracking active local development tunnels requires constant polling. By feeding the `list_endpoints` tool into a Mastra agent, you create a dedicated monitoring pipeline. The workflow engine requests the active endpoints and filters for unauthorized domains. Sometimes these network calls drop. Mastra detects the Streamable HTTP transport automatically when you initialize the MCPClient. If the connection to Vinkius stutters while fetching `list_reserved_domains`, the agent pauses, recovers, and completes the audit.

Setup guide

Set up ngrok 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 ngrok 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: "ngrok-mcp-client",
  servers: {
    "ngrok-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent ngrok 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 ngrok. 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 ngrok 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 ngrok MCP in Mastra AI

Install `@mastra/mcp@latest`. Create a new `MCPClient` instance and pass the Vinkius URL into the servers object. Mastra auto-detects whether to use SSE or Streamable HTTP.

Yes. You can configure `requireToolApproval` on the agent. When the workflow attempts to run `list_ip_policies`, it pauses execution until an admin clicks approve.

Network timeouts or 500-level HTTP errors from the ngrok API trigger Mastra's exponential backoff. The workflow engine will automatically re-attempt the tool execution based on your retry configuration.

Call `mcpClient.listTools()` and spread the result into your agent's tool array. The workflow will immediately understand how to query endpoints and vaults.

No. The MCP standard operates on a strict zero-trust model. When your agent calls `list_ip_policies`, the Vinkius endpoint fetches the access lists and pipes them directly back to your Mastra runtime. The execution environment is completely ephemeral, meaning no network rules are ever cached or logged on external disks.

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