How to Use the Bunny.net MCP in LangChain

Q: Can LangChain handle bulk invalidation across multiple Bunny.net zones?

Yes, the agent can fetch all active zones using listpullzones and loop through them. It then triggers purgepullzone for each targeted CDN domain sequentially.

Spin up Bunny.net CDN zones and purge edge caches directly within your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect Bunny.net to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fast Edge Deployments via LangChain

The `add_pull_zone` tool lets your agent build and tear down global delivery setups on the fly. By triggering this action, the LLM sets up a live reverse proxy immediately after generating static assets. You don't have to log into a dashboard or write custom curl scripts to link your content. LangSmith tracks every step of this execution. If a zone creation fails or times out, you see the raw API payload right in your trace logs. The agent can catch the error and try a different region if needed.

Smart Cache Clearing on LangChain Events

The `purge_pull_zone` tool lets your pipeline clear edge content instantly when database records change. This replaces manual invalidation strategies with event-driven execution. Your users get the newest assets without waiting for TTLs to expire. Passing the output of `list_pull_zones` straight into the purge tool ensures you only hit active domains. This chain keeps your origin server safe from accidental traffic spikes by target-purging only what changed.

Dynamic Storage Provisioning with MCP Server Tools

The `add_storage_zone` tool sets up storage buckets on demand during complex multi-step tasks. The agent evaluates the size of your assets, claims your namespace, and configures replication rules. Once the storage is ready, the agent pulls credentials using `get_storage_zone`. This lets subsequent steps in your LangChain pipeline write files directly to the newly minted origin without hardcoding secrets beforehand.

Setup guide

Set up Bunny.net MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Bunny.net tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "bunnynet-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Bunny.net transactions"
    })
    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 LangChain

Install the adapter package and point the client to your Vinkius endpoint. From there, extract the tools and pass them directly to your agent constructor to let it manage CDN configurations.

Yes, the agent can fetch all active zones using `list_pull_zones` and loop through them. It then triggers `purge_pull_zone` for each targeted CDN domain sequentially.

Use LangSmith tracing to monitor every tool call. You will see the exact milliseconds it takes to execute commands like `list_files` or zone creation.

The tool returns the raw API error to the model. Your agent can then decide to retry `delete_pull_zone` or flag the issue for human review.

Vinkius handles the credentials in a secure MCP sandbox, so your LLM never sees the master API key. It only interacts with the specific tools like `get_storage_zone` to retrieve ephemeral FTP credentials when needed.

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