How to Use the Cloudflare Tunnel MCP in AutoGen

Q: What happens if a tunnel route creation fails during a multi-agent task?

The agent executing createroute will receive the error message and post it to the group chat. The other agents will analyze the error and suggest alternative routing paths.

Deploy multi-agent debates in AutoGen to safely negotiate and execute Cloudflare Tunnel configurations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudflare Tunnel MCP to AutoGen

Create your Vinkius account to connect Cloudflare Tunnel to AutoGen 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 Cloudflare Tunnel with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate Cloudflare Tunnel Setups in AutoGen

The `create_tunnel` tool enables your AutoGen security and operations agents to negotiate network setups before they execute. This MCP Server allows your security agent to review the parameters of `create_tunnel` before the operations agent executes it. If the operations agent attempts to create a tunnel with overly permissive settings, the security agent flags it. They negotiate the configuration until they agree on the safest parameters for `put_configuration`.

Collaborative Route Troubleshooting

Your agents call `get_route_by_ip` to diagnose and coordinate fixes for routing failures in your network. When a route fails, a single agent might miss the cause, but in AutoGen, a diagnostic agent can call `get_route_by_ip` while a network agent checks `list_connections` to find the bottleneck. The agents discuss the findings in a group chat. Once they locate the issue, they coordinate a fix, calling `update_route` to restore traffic flow without human intervention.

Automated Connection Auditing

The `list_connections` tool allows your AutoGen auditor agent to scan for inactive links periodically. This MCP Server enables deep inspection of your network topology to locate stale connectors that pose security risks. The auditor agent then presents these findings to a manager agent. If the manager agent approves, the auditor agent invokes `cleanup_connections` to secure the perimeter.

Setup guide

Set up Cloudflare Tunnel MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Cloudflare Tunnel tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Cloudflare Tunnel_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cloudflare Tunnel data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Cloudflare Tunnel_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cloudflare Tunnel data")
    print(result.messages[-1].content)

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 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.

Connect Cloudflare 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 Cloudflare Tunnel MCP in AutoGen

Agents use a structured debate loop to verify settings. If one agent tries to run `update_tunnel` with invalid parameters, the peer agent catches the error and proposes a corrected configuration.

Yes, you can configure AutoGen to pause before executing critical tools like `delete_tunnel`. The agent will present the proposed action to you in the chat, waiting for your approval before calling the MCP Server.

AutoGen agents retrieve the necessary tokens dynamically using `get_management_token`. The token is handled in memory and passed directly to the execution tool, minimizing the risk of exposure in the conversation logs.

The agent executing `create_route` will receive the error message and post it to the group chat. The other agents will analyze the error and suggest alternative routing paths.

Your management tokens and configuration details are processed entirely within the Vinkius zero-trust sandbox. The MCP Server executes each tool call in an ephemeral, isolated environment, ensuring your network credentials never touch external logs or persistent storage.

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