4,500+ servers built on MCP Fusion
Vinkius
Cloudflare Tunnel logo
Vinkius
OpenAI Agents SDK logo

How to Use the Cloudflare Tunnel MCP in OpenAI Agents SDK

Secure your production OpenAI Agents SDK workflows by letting your agents spin up and tear down Cloudflare Tunnels on demand.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Cloudflare Tunnel MCP on Cursor AI Code Editor MCP Client Cloudflare Tunnel MCP on Claude Desktop App MCP Integration Cloudflare Tunnel MCP on OpenAI Agents SDK MCP Compatible Cloudflare Tunnel MCP on Visual Studio Code MCP Extension Client Cloudflare Tunnel MCP on GitHub Copilot AI Agent MCP Integration Cloudflare Tunnel MCP on Google Gemini AI MCP Integration Cloudflare Tunnel MCP on Lovable AI Development MCP Client Cloudflare Tunnel MCP on Mistral AI Agents MCP Compatible Cloudflare Tunnel MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect Cloudflare Tunnel MCP to OpenAI Agents SDK

Create your Vinkius account to connect Cloudflare Tunnel 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

Let OpenAI Agents SDK build secure routes on the fly

Your production agents need a way to reach private databases without opening public ports. This MCP Server exposes tools like `create_tunnel` and `create_route` directly to your OpenAI Agents SDK runtime, allowing your system to establish encrypted paths to isolated infrastructure during execution. Your agent checks active paths via `list_routes` and updates them with `update_route` if network demands shift. Because the MCP Server runs in the Vinkius sandbox, your API keys stay isolated while your agent safely maps out the required network topology.

Automated configuration and token management

When building multi-agent systems, you need tight control over credentials. The agent can use `get_tunnel_token` and `get_management_token` to configure local connectors without human intervention. Once the credentials are in hand, the agent pushes new routing rules using `put_configuration` and `get_configuration`. This lets your OpenAI pipeline bootstrap its own secure tunnels, run its tasks, and keep configuration states synchronized.

Safe teardown and connection cleanup

Leaving idle tunnels open is a major security risk in production. Your agent can monitor active links with `list_connections` and immediately close stale pathways using `cleanup_connections` when a task finishes. If a temporary tunnel is no longer needed, the agent calls `delete_tunnel` and `delete_route` to wipe the slate clean. This ensures your private network footprint shrinks back to zero the moment your OpenAI pipeline completes its run.

Setup guide

Set up Cloudflare Tunnel 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. 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. 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 Cloudflare Tunnel tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cloudflare Tunnel 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="Cloudflare Tunnel Agent",
            instructions="You have access to Cloudflare Tunnel tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cloudflare Tunnel. 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.

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 Cloudflare Tunnel MCP in OpenAI Agents SDK

Run `pip install openai-agents` first. Then, initialize the connection using `MCPServerStreamableHttp` with your Vinkius endpoint URL and pass it to your Agent constructor inside the `mcp_servers` list.
Yes, your agent can troubleshoot its own connections. If a connection drops, the agent can call `get_connector` to inspect the health of the tunnel and re-run `create_route` if the path is missing.
Absolutely. You can have a specialized network agent handle `create_tunnel` and `get_tunnel_token`, then hand off the connection details to a database agent that queries the newly exposed endpoint.
The agent can fetch the current state using `get_configuration`, modify the routing parameters, and apply the changes using `put_configuration` or `update_tunnel`.
Vinkius processes your Cloudflare credentials and tunnel configurations in an ephemeral, zero-trust V8 sandbox. No sensitive tunnel tokens or routing data are ever persisted or written to disk.

Start using the Cloudflare Tunnel MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 17 tools

We've already built the connector for Cloudflare Tunnel. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 17 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.