How to Use the Cloudflare Tunnel MCP in LangChain

Q: How do I handle failed tunnel creation inside a chain?

You catch the error in your LangChain execution loop. If createtunnel fails due to a name conflict, the agent can list existing setups with listtunnels and choose a unique name.

Spin up secure Cloudflare Tunnels and manage Zero Trust routes directly within your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect Cloudflare Tunnel to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Cloudflare Tunnels in LangChain Chains

The `create_tunnel` tool lets your LangChain agent securely expose local services without manual CLI work. This MCP Server allows your chain to run `create_tunnel` and `put_configuration` in a single, fluid execution. LangSmith traces the exact parameters passed to Cloudflare, showing you the tunnel token generation in real time. You can build multi-step chains where the first step provisions a tunnel and the next step calls `create_route` to map private IPs. Because LangChain handles state transitions between tool calls, your agent knows exactly when the tunnel is active and ready for traffic routing.

Automated Connection Cleanup

Your LangChain agent uses `cleanup_connections` to remove stale connectors and keep your network topology clean. Stale connectors mess up your network topology and waste resources, but your agent can run a cleanup step right after a testing run completes. The agent inspects active links using `list_connections` and decides if they are still needed. If a connection is orphaned, the chain automatically invokes the cleanup tool to tear down the tunnel safely without manual oversight.

Dynamic Route Management

The `get_route_by_ip` tool allows LangChain chains to inspect existing network paths before making routing changes. Managing routing tables across multiple private networks is tedious, but this MCP Server lets your agent check paths instantly. If a conflict is found, the agent can call `update_route` or `delete_route` to clear the path. Your agent handles the logic, and the server handles the actual infrastructure changes.

Setup guide

Set up Cloudflare Tunnel MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Cloudflare Tunnel tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "cloudflare-tunnel-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Cloudflare Tunnel transactions"
    })
    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 LangChain

LangChain passes the token securely through environment variables when invoking `get_tunnel_token`. The token never gets logged in your LangSmith traces because the MCP Server handles the credential exchange in a secure sandbox.

Yes, you can set up a ReAct loop that monitors connections. If `list_connections` shows a down tunnel, LangChain can automatically call `get_management_token` to restart or reconfigure the connector.

Yes, you can combine this server with other MCP tools using LangChain's MultiServerMCPClient. This lets your agent provision a Cloudflare Tunnel and immediately configure a local database on that same tunnel.

You catch the error in your LangChain execution loop. If `create_tunnel` fails due to a name conflict, the agent can list existing setups with `list_tunnels` and choose a unique name.

Your tunnel configuration data and management tokens remain inside the Vinkius secure sandbox. The server only passes the final API calls to Cloudflare via encrypted endpoints, meaning your private IP addresses never leak to the public internet or external LLM providers.

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