How to Use the Cloudflare Tunnel MCP in Google ADK

Q: How do I configure my Google ADK agent to use the Cloudflare Tunnel MCP Server?

Install the library with pip install google-adk and instantiate McpToolset pointing to your Vinkius HTTP endpoint. Pass this toolset directly into your LlmAgent constructor to expose the tunnel management capabilities.

Q: Can a Google ADK agent troubleshoot a broken Cloudflare Tunnel connection?

Yes, your agent can run getconnector and listconnections to diagnose why a tunnel is offline. It can then use those diagnostics to re-establish the connection or notify your team.

Q: Is it safe to let Gemini handle Cloudflare Tunnel MCP Server commands in Google ADK?

Yes, you can use the ADK's toolnames filter to restrict the agent to read-only tools like listtunnels and gettunnel if you want to prevent unauthorized modifications.

Q: How do I clean up stale routes?

The agent can query active routes with listroutes and remove any that are no longer in use by executing deleteroute.

Give Google ADK agents the power to spin up Cloudflare Tunnels and link Gemini to private BigQuery datasets safely.

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 Google ADK

Create your Vinkius account to connect Cloudflare Tunnel to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Expose private backend data to Google ADK

Gemini needs access to your private databases, but you can't expose them to the open web. This MCP Server lets your Google ADK agent run `create_tunnel` and `create_route` to open temporary, encrypted paths directly to your internal storage. The agent checks existing network paths using `list_routes` and `get_route_by_ip` to locate your private services. It can then pull data through the secure tunnel, feeding clean context directly into Gemini's massive 1M+ token window.

Dynamic tunnel configuration through Google ADK

Instead of hardcoding network paths, let your Google ADK agent adapt on the fly. The agent can read existing setups with `get_configuration` and instantly apply new routing rules using `put_configuration`. If network parameters change, the agent executes `update_tunnel` and `update_route` to keep traffic flowing. This gives your Google Cloud enterprise agent the flexibility to manage its own ingress points without manual DevOps tickets.

Automated credential provisioning and cleanup

To spin up local tunnel connectors, your agent needs credentials. The agent can invoke `get_tunnel_token` and `get_management_token` to grab the necessary tokens and pass them to your local container environments. When the enterprise job finishes, the agent keeps your network clean by calling `cleanup_connections` and `delete_tunnel`. This ensures no orphaned tunnels or exposed routes linger after the agent finishes its work.

Setup guide

Set up Cloudflare Tunnel MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Cloudflare Tunnel tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Cloudflare Tunnel_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cloudflare Tunnel tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install the library with `pip install google-adk` and instantiate `McpToolset` pointing to your Vinkius HTTP endpoint. Pass this toolset directly into your `LlmAgent` constructor to expose the tunnel management capabilities.

Yes, your agent can run `get_connector` and `list_connections` to diagnose why a tunnel is offline. It can then use those diagnostics to re-establish the connection or notify your team.

Yes, you can use the ADK's `tool_names` filter to restrict the agent to read-only tools like `list_tunnels` and `get_tunnel` if you want to prevent unauthorized modifications.

The agent can query active routes with `list_routes` and remove any that are no longer in use by executing `delete_route`.

All Cloudflare Tunnel tokens, management credentials, and route configurations are processed in memory within Vinkius's isolated V8 sandbox. No credential data is logged or stored, maintaining strict zero-trust isolation between your Google ADK runtime and Cloudflare.

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