How to Use the Bunny.net MCP in Pydantic AI

Q: How do I initialize Bunny.net within Pydantic AI?

Use the unified MCPToolset class pointing to the Vinkius HTTP endpoint for your MCP Server. Pass this toolset to your agent constructor to expose the CDN and storage tools.

Q: Can I use Pydantic AI to safely delete Bunny.net zones?

Yes, because the input fields for deletepullzone are strictly validated against Pydantic schemas. The agent cannot pass malformed IDs to the destruction tool.

Control Bunny.net edge configurations using this MCP Server with the strict, type-safe runtime validation of Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Bunny.net to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pydantic AI Type-Safe CDN State Management

Working with CDN states requires absolute data integrity. This MCP Server ensures that every response from `get_pull_zone` matches strict schemas before your Pydantic AI agent processes the data. If Bunny.net returns unexpected SSL parameters or bandwidth formats, the framework fails immediately. This prevents your agent from acting on corrupt configurations and misconfiguring your production routing.

Validated Storage Zone Provisioning

When creating storage, your agent needs to handle credentials without silent errors. The `add_storage_zone` tool returns a structured payload that Pydantic AI validates at the runtime layer. Your agent uses `get_storage_zone` to fetch FTP keys, ensuring the exact string format matches your system requirements. This strict type checking means zero hallucinated fields when uploading assets.

Safe File and Cache Operations

Destructive actions like `delete_pull_zone` require validated inputs to prevent accidental downtime. Your Pydantic AI agent validates the target zone ID before executing the teardown sequence. When clearing caches, the agent fires `purge_pull_zone` and validates the origin re-fetch response. This guarantees your pipeline receives a clean confirmation instead of a silent failure.

Setup guide

Set up Bunny.net MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "bunnynet-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Bunny.net tools.",
)

result = await agent.run("List recent Bunny.net transactions")
print(result.output)

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 Pydantic AI

Use the unified `MCPToolset` class pointing to the Vinkius HTTP endpoint for your MCP Server. Pass this toolset to your agent constructor to expose the CDN and storage tools.

The framework raises a validation error immediately. This loud failure prevents the agent from making dangerous routing decisions based on corrupted payload structures.

Yes, because the input fields for `delete_pull_zone` are strictly validated against Pydantic schemas. The agent cannot pass malformed IDs to the destruction tool.

The server runs externally on Vinkius, allowing your Pydantic AI agent to connect via streamable HTTP or SSE transports using the unified toolset setup.

Your API tokens are managed securely in Vinkius. The Pydantic AI framework only validates the resulting schema of tools like `list_files`, keeping the underlying keys safe from exposure.

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