How to Use the Bunny.net MCP in AutoGen

Q: Can one AutoGen agent create a Bunny.net zone and another delete it?

Yes, the conversational workflow allows one agent to run addstoragezone and another to clean up using deletestoragezone once the task finishes.

Let AutoGen agents debate and coordinate your Bunny.net CDN deployments and cache purges.

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 AutoGen

Create your Vinkius account to connect Bunny.net 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 Bunny.net with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven CDN Management in AutoGen

The `add_pull_zone` tool lets your performance agent spin up new CDN setups after a group debate. With this MCP Server, your performance agent can argue for a new zone, while a security agent reviews the settings. They debate the configuration until they reach agreement. Only then does the execution agent run the tool to spin up the CDN.

Cooperative Storage Cleanup Pipelines

The `list_files` tool lets one agent catalog assets before another agent runs a cleanup. This workflow avoids accidental data loss during storage teardowns by introducing a verification step. Once both agents approve, they execute `delete_storage_zone`. This multi-agent verification loop prevents catastrophic mistakes in production.

Automated Incident Response and Cache Purging

The `purge_pull_zone` tool clears the bad cache as soon as a monitoring agent flags an issue. When a monitoring agent detects an issue, it alerts the coordinator, which tasks a sub-agent to run the purge. A separate agent checks the status using `get_pull_zone` to confirm the fix. This distributed workflow resolves edge issues without human intervention.

Setup guide

Set up Bunny.net 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 Bunny.net 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="Bunny.net_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Bunny.net 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="Bunny.net_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Bunny.net 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 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 AutoGen

You register the server tools with the user proxy or assistant agents. Any agent in the group chat can then trigger commands like `list_pull_zones` based on the conversation flow.

Yes, the conversational workflow allows one agent to run `add_storage_zone` and another to clean up using `delete_storage_zone` once the task finishes.

You can set rate limits on the Vinkius proxy or configure a critic agent to approve calls to `purge_pull_zone` before they execute.

The conversation continues until the termination condition is met. If they do not agree, the tool call is skipped, protecting your origin server.

The key is injected securely at the Vinkius MCP transport layer. Agents only see the high-level tool schemas and execution results, never the raw authentication tokens.

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