How to Use the Backblaze B2 MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK manage Backblaze B2 bucket creation?

Your agent calls the createbucket tool from this MCP Server. The SDK lets you build agents that can safely provision new B2 buckets as part of a larger, automated task.

Q: Can I clean up failed uploads in Backblaze B2 with an OpenAI agent?

Yes. The listunfinishedlargefiles tool is designed for this. Your OpenAI agent can periodically scan for and report stalled multipart uploads in your Backblaze B2 account.

Q: What happens if my OpenAI agent tries to delete a non-empty Backblaze B2 bucket?

The deletebucket tool will intentionally fail with an error. Your OpenAI agent can be programmed to handle this specific error, preventing accidental data loss and allowing for more robust automation.

Q: How do I get the bucket ID I need for file operations?

Use the listbuckets tool. It returns the names and immutable string IDs for all buckets in your account, which you'll need for most other tool calls.

Deploy agents that manage Backblaze B2 storage, backed by the safety and tracing of the 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 Backblaze B2 MCP to OpenAI Agents SDK

Create your Vinkius account to connect Backblaze B2 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 Backblaze B2 with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Bucket Lifecycle

Give your agent the tools to manage Backblaze B2 buckets from start to finish. It can provision a new storage partition with `create_bucket` before a data sync job, and then tear it down cleanly afterwards. You get the exact bucket IDs you need for other operations by calling `list_buckets`. Because the OpenAI Agents SDK has built-in guardrails, you can let your agent handle destructive operations with more confidence. For example, the `delete_bucket` tool will fail if the bucket isn't empty. Your agent can catch this specific failure, log it, and move on without bringing down your whole workflow. It's autonomous, but not reckless.

Traceable File Operations with Your MCP Server

Perform surgical changes to your B2 files. Your agent can call `delete_file_version` to get rid of a specific data chunk, which is great for managing storage costs and compliance. For less permanent changes, `hide_file` marks an object as hidden without actually deleting the data, letting your lifecycle rules handle the final cleanup. Every action is fully traceable in the OpenAI dashboard. You can see the exact moment your agent called `get_file_info` on a file or hid an object from public view. This gives you a clear audit trail for everything your agent does inside your B2 account.

Run Auditable B2 Maintenance

Turn common B2 maintenance chores into automated agent tasks. Let your agent run a daily check for broken uploads with `list_unfinished_large_files`. It can find stalled multipart uploads from other clients and flag them for cleanup, saving you from having to script this yourself. Your agent can also manage access rules. It can use `update_bucket` to change a bucket's privacy settings, like making a static asset bucket public. This MCP server connects your agent directly to the B2 API, so these operations happen instantly.

Setup guide

Set up Backblaze B2 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 Backblaze B2 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Backblaze B2 tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Backblaze B2 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="Backblaze B2 Agent",
            instructions="You have access to Backblaze B2 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 Backblaze B2. 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 Backblaze B2 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 Backblaze B2 MCP in OpenAI Agents SDK

Your agent calls the `create_bucket` tool from this MCP Server. The SDK lets you build agents that can safely provision new B2 buckets as part of a larger, automated task.

Yes. The `list_unfinished_large_files` tool is designed for this. Your OpenAI agent can periodically scan for and report stalled multipart uploads in your Backblaze B2 account.

The `delete_bucket` tool will intentionally fail with an error. Your OpenAI agent can be programmed to handle this specific error, preventing accidental data loss and allowing for more robust automation.

Use the `list_buckets` tool. It returns the names and immutable string IDs for all buckets in your account, which you'll need for most other tool calls.

This server only handles metadata about your B2 account. It processes things like bucket names, file lists, object headers, and checksums. Your raw B2 credentials and the actual contents of your files are never exposed to or stored by the Vinkius MCP Server.

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