Can I check if a file is publicly accessible through the agent?

Yes. The `get_object_access_control` tool allows your AI agent to retrieve the Access Control List (ACL) for any specific file, helping you audit permissions and identify public objects.

How do I protect my files from accidental deletion in a bucket?

You can use the `enable_bucket_versioning` tool to activate versioning on your bucket. This ensures that historical copies of your files are preserved, allowing you to recover from accidental overwrites or deletions.

Can I see where my data is physically stored?

Absolutely. Use the `get_bucket_datacenter_location` tool to retrieve the specific geographic region where a bucket is hosted, ensuring you meet data residency requirements.

Wasabi MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Wasabi
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Wasabi through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Wasabi Assistant",
            instructions=(
                "You help users interact with Wasabi. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Wasabi"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Wasabi MCP Server

Connect your Wasabi Hot Cloud Storage account to any AI agent and take full control of your cloud assets through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Wasabi through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Wasabi, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Bucket Management — List all storage buckets, create new ones, or delete obsolete containers in your account
Object Discovery — Browse and list files (objects) stored within specific buckets, including sizes and last modified dates
Data Integrity — Enable and check bucket versioning to protect against accidental file overwrites or deletions
Access Control — Audit permissions and retrieve Access Control Lists (ACL) for specific files to ensure security
Data Residency — Verify the physical geographic region where your data is hosted for compliance needs
Cleanup Tasks — Identify fractured file uploads that consume storage and permanently delete obsolete assets

The Wasabi MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Wasabi to OpenAI Agents SDK via MCP

Follow these steps to integrate the Wasabi MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Wasabi

Why Use OpenAI Agents SDK with the Wasabi MCP Server

OpenAI Agents SDK provides unique advantages when paired with Wasabi through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Wasabi + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Wasabi MCP Server delivers measurable value.

Automated workflows: build agents that query Wasabi, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Wasabi, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Wasabi tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Wasabi to resolve tickets, look up records, and update statuses without human intervention

Wasabi MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Wasabi to OpenAI Agents SDK via MCP:

create_storage_bucket

Provide a globally unique lower-kebab-case name. Creates a new high-availability storage bucket in the configured Wasabi region

delete_bucket_object

This action is irreversible. Permanently deletes a specific file from a bucket

delete_storage_bucket

Note: The bucket must be completely empty first. This action is irreversible. Permanently removes an empty storage bucket

enable_bucket_versioning

Activates object versioning for a bucket

get_bucket_datacenter_location

Retrieves the physical geographic region where a bucket is hosted

get_bucket_versioning_status

Checks if object versioning is enabled for a bucket

get_object_access_control

Retrieves the access control list (ACL) for a specific file

list_bucket_objects

Returns file keys, sizes, and last modified dates. Lists the files (objects) stored within a specific bucket

list_pending_multipart_uploads

Lists incomplete multipart uploads in a bucket

list_storage_buckets

Lists all Wasabi storage buckets visible to the authenticated IAM user

Example Prompts for Wasabi in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Wasabi immediately.

"List all my storage buckets in Wasabi."

"What files are inside the 'backups-2026' bucket?"

"Is versioning enabled for my 'user-data-prod' bucket?"

Troubleshooting Wasabi MCP Server with OpenAI Agents SDK

Common issues when connecting Wasabi to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Wasabi + OpenAI Agents SDK FAQ

Common questions about integrating Wasabi MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.