How to Use the ngrok MCP in OpenAI Agents SDK

Q: How do I secure my ngrok tunnels using OpenAI Agents SDK?

You configure your agent to call listippolicies and listiprestrictions regularly. This ensures you can verify that only authorized traffic reaches your local services.

Q: Can OpenAI Agents SDK monitor my ngrok endpoint usage?

Yes. By using the listendpoints tool, your agent pulls real-time data on active tunnels. It reports back exactly which services are currently exposed.

Q: Does ngrok MCP Server work with my existing OpenAI Agents SDK setup?

It integrates directly via the MCPServerStreamableHttp constructor. You define the server, pass it to your agent, and the tools are ready to use.

Q: What happens if my ngrok API keys are leaked?

You use the listapikeys tool to audit your active credentials. If you see an unrecognized key, you know to rotate it immediately via the dashboard.

Manage your tunnels and security policies directly within OpenAI Agents SDK for production-grade ingress visibility.

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 OpenAI Agents SDK

Create your Vinkius account to connect ngrok to OpenAI Agents 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 ngrok with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit your tunnel infrastructure

Your agent queries `list_endpoints` and `list_https_edges` to track exactly what you have exposed to the public internet. It catches rogue tunnels before they become a security headache. Automating this discovery saves you from manual dashboard checks. The agent flags active connections immediately, keeping your infrastructure audit trail clean.

Verify security policies with your agent

The MCP Server allows your agent to inspect `list_ip_policies` and `list_ip_restrictions` to confirm your ingress rules match your expectations. You get real-time verification of your edge configurations. Don't guess if your firewall rules are active. Your agent checks the source of truth directly, ensuring no misconfigured policy leaves your services vulnerable.

Manage your domain and key lifecycle

Your agent uses `list_reserved_domains` and `list_api_keys` to keep an inventory of your assets. This eliminates the risk of stale keys lingering in your environment. Keep your project organized by letting the agent surface expiring domains or unused credentials. It provides the visibility needed to rotate secrets on a predictable schedule.

Setup guide

Set up ngrok MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all ngrok tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives ngrok tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate ngrok tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="ngrok Agent",
            instructions="You have access to ngrok tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You configure your agent to call `list_ip_policies` and `list_ip_restrictions` regularly. This ensures you can verify that only authorized traffic reaches your local services.

Yes. By using the `list_endpoints` tool, your agent pulls real-time data on active tunnels. It reports back exactly which services are currently exposed.

It integrates directly via the `MCPServerStreamableHttp` constructor. You define the server, pass it to your agent, and the tools are ready to use.

You use the `list_api_keys` tool to audit your active credentials. If you see an unrecognized key, you know to rotate it immediately via the dashboard.

The server only reads metadata from your account via HTTPS. Your sensitive traffic payloads remain untouched, as the connection only pulls configuration lists like `list_vaults`.

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