How to Use the Cloudflare MCP in Google ADK

Q: How do I register the Cloudflare MCP Server inside Google ADK?

Instantiate McpToolset with the Vinkius HTTP transport URL. Pass that toolset object into your LlmAgent tools array to give Gemini direct access to the edge tools.

Q: Can Gemini use the Google ADK to query Cloudflare D1 databases?

Yes. The agent uses queryd1 to execute raw SQL queries like SELECT, INSERT, or UPDATE directly against your D1 instances. It handles the JSON output natively within its context window.

Q: Can I limit which Cloudflare tools are exposed to my Google ADK agent?

Yes. You can pass a filtered list of allowed tools to the McpToolset constructor. This prevents the agent from accessing destructive operations like deleteworker while still allowing read-only analytics.

Q: How secure are my Cloudflare KV store values when accessed via Google ADK?

KV values retrieved via getkvkey are transmitted over encrypted Vinkius HTTP tunnels directly to your agent. No data is cached on intermediary servers, keeping user sessions and configuration keys private.

Feed edge analytics into Gemini's million-token context window using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cloudflare MCP to Google ADK

Create your Vinkius account to connect Cloudflare 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 with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed edge analytics to Google ADK reasoning loops

Gathering edge traffic metrics is managed by the `get_zone_analytics` tool to identify anomalous spikes. Gemini's massive context window is perfect for analyzing these traffic patterns. Your agent can pull 24 hours of performance metrics using `get_worker_analytics` to identify elevated error rates. Once the agent digests this data, it can write a mitigation script and deploy it instantly. The Google ADK coordinates this by calling `create_worker_route` to route malicious traffic to a honeypot Worker, protecting your origin.

Sync BigQuery datasets with Cloudflare D1

Syncing edge database records is handled by the `query_d1` tool to execute updates directly on your instances. Keep your edge database in sync with your enterprise data warehouse. Your agent can read records from BigQuery, format the payload, and write it to your edge database. This MCP Server allows your Google ADK agent to check existing databases using `list_d1_databases` before executing updates. It ensures your edge applications always have the latest business logic without manual sync scripts.

Manage static assets and R2 storage

Managing media assets at the edge uses the `list_r2_buckets` tool to inspect your active storage. Let Gemini inspect and organize your media assets at the edge. The agent lists your storage buckets and clears obsolete assets from the CDN cache using `purge_cache` to keep hosting costs down. Because Google ADK integrates natively with Vertex AI, you can build agents that analyze asset trends. They generate optimized configurations and write those updates directly back to KV namespaces using `list_kv_keys`.

Setup guide

Set up Cloudflare 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 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_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Cloudflare 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. 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 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 MCP in Google ADK

Instantiate `McpToolset` with the Vinkius HTTP transport URL. Pass that toolset object into your `LlmAgent` tools array to give Gemini direct access to the edge tools.

Yes. The agent uses `query_d1` to execute raw SQL queries like SELECT, INSERT, or UPDATE directly against your D1 instances. It handles the JSON output natively within its context window.

Gemini's long-context window easily processes the large JSON payloads returned by `get_zone_analytics`. The agent can spot trends across thousands of data points without running out of memory.

Yes. You can pass a filtered list of allowed tools to the `McpToolset` constructor. This prevents the agent from accessing destructive operations like `delete_worker` while still allowing read-only analytics.

KV values retrieved via `get_kv_key` are transmitted over encrypted Vinkius HTTP tunnels directly to your agent. No data is cached on intermediary servers, keeping user sessions and configuration keys private.

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