How to Use the Bunny.net MCP in Google ADK

Q: How do I connect the Bunny.net MCP Server to my Google ADK agent?

Instantiate McpToolset using the streamable HTTP transport parameters pointing to the Vinkius URL. Then, pass this toolset directly into your Google ADK LlmAgent configuration.

Q: Is it possible to limit which Bunny.net tools the Google ADK agent can access?

You can use the optional tool name filter during your McpToolset setup. This lets you expose only read-only operations like listpullzones while hiding destructive commands from your MCP setup.

Q: How does the agent handle regional storage configuration?

The addstoragezone tool automatically defaults to NY-based replication volumes. Your Google ADK agent can coordinate this with your GCS buckets to maintain multi-cloud storage parity.

Q: How are the Bunny.net FTP credentials protected in Google ADK?

The getstoragezone tool returns credentials securely within the Vinkius runtime. They are parsed by the Google ADK agent to perform actions but are never written to your BigQuery logs or Vertex AI training sets.

Feed live Bunny.net edge metrics and storage data into your Google ADK pipelines using our dedicated MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bunny.net MCP to Google ADK

Create your Vinkius account to connect Bunny.net 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 Bunny.net with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Pipeline Sync via Google ADK

Enterprise data sitting in BigQuery often needs direct synchronization with your CDN assets. Using this MCP Server, your Google ADK agent queries active targets with `list_pull_zones` and compares them to database records. If inconsistencies appear, the Gemini model uses its long-context window to analyze the discrepancy. It then triggers `add_pull_zone` to spin up missing reverse proxies without human intervention.

Edge Storage Auditing with Gemini Reasoning

Gemini's 1M+ token context allows you to analyze massive file structures at once. Your Google ADK agent executes `list_storage_zones` and `list_files` to ingest entire folder trees into Vertex AI. The agent processes file hashes and byte lengths to detect duplicate or orphaned media assets. Once identified, it calls `delete_storage_zone` to reclaim space on your Bunny.net storage backend.

Automated Routing and Cache Management

High-traffic enterprise applications require instant cache clearing during continuous integration. Your Google ADK agent watches cloud triggers and fires `purge_pull_zone` to force immediate origin re-fetching. It monitors the impact by calling `get_pull_zone` to read bandwidth limits and edge rules. This telemetry feeds back into your Google Cloud monitoring console to keep performance metrics unified.

Setup guide

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

Instantiate `McpToolset` using the streamable HTTP transport parameters pointing to the Vinkius URL. Then, pass this toolset directly into your Google ADK `LlmAgent` configuration.

Yes, because the Google ADK leverages Gemini's million-token context. The agent can call `list_files` to retrieve extensive directory maps and process them in a single reasoning loop.

You can use the optional tool name filter during your `McpToolset` setup. This lets you expose only read-only operations like `list_pull_zones` while hiding destructive commands from your MCP setup.

The `add_storage_zone` tool automatically defaults to NY-based replication volumes. Your Google ADK agent can coordinate this with your GCS buckets to maintain multi-cloud storage parity.

The `get_storage_zone` tool returns credentials securely within the Vinkius runtime. They are parsed by the Google ADK agent to perform actions but are never written to your BigQuery logs or Vertex AI training sets.

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