How to Use the Wasabi MCP in OpenAI Agents SDK

Q: What happens if I run a deletion via Wasabi through the OpenAI Agents SDK?

Deletions are irreversible, so be careful. The deletebucketobject tool permanently removes files, and the agent will confirm this action before proceeding. You'll get clear feedback on every destructive operation.

Q: Does Wasabi support versioning with the OpenAI Agents SDK?

Yes, it does. The enablebucketversioning tool activates object versioning for any bucket your agent interacts with. This means if a file is changed or deleted, the previous versions are still recoverable.

Manage high-performance data residency for your OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wasabi MCP to OpenAI Agents SDK

Create your Vinkius account to connect Wasabi to OpenAI Agents SDK 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 Wasabi with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient storage pipelines.

The `create_storage_bucket` tool lets you spin up a new, high-availability bucket in the configured Wasabi region. Your agent can guarantee data residency by creating and managing these core storage buckets automatically. Need to clean house? Use `delete_storage_bucket` when an empty bucket needs permanent removal. This helps keep your agent's operational scope tight.

Track file changes and versions.

Want to know what files are in a specific bucket? The `list_bucket_objects` tool returns keys, sizes, and last modified dates. This gives your agent the full inventory it needs before writing anything. Furthermore, you can enable versioning using `enable_bucket_versioning`. If something gets deleted or overwritten, the system keeps a record via `get_bucket_versioning_status`.

Manage object access and lifecycle.

When your agent needs to know who can read certain files, it calls `get_object_access_control`. This checks the specific file's Access Control List (ACL) before any action is taken. If you suspect incomplete uploads, running `list_pending_multipart_uploads` helps your production system find and finish those jobs. It’s a crucial safety check for data integrity.

Setup guide

Set up Wasabi MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Wasabi tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Wasabi tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Wasabi tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Wasabi Agent",
            instructions="You have access to Wasabi tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Wasabi. 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 Wasabi 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 Wasabi MCP in OpenAI Agents SDK

The MCP Server auto-discovers all Wasabi tools when your agent initializes. Your specialized agents can then call storage actions directly without needing custom code. The built-in guardrails validate every action, making it safe for production use.

Absolutely. You can program your agents to list buckets using `list_storage_buckets` and then execute `delete_storage_bucket` on empty ones. This ensures that ephemeral data is removed when its job is done.

Deletions are irreversible, so be careful. The `delete_bucket_object` tool permanently removes files, and the agent will confirm this action before proceeding. You'll get clear feedback on every destructive operation.

Yes, it does. The `enable_bucket_versioning` tool activates object versioning for any bucket your agent interacts with. This means if a file is changed or deleted, the previous versions are still recoverable.

This MCP Server manages object data and bucket metadata. Specifically, it handles the creation, listing, and permanent deletion of files (objects) within your defined storage buckets.

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