How to Use the Backblaze B2 MCP in AutoGen

Q: Can AutoGen agents delete a Backblaze B2 bucket without my approval?

Only if you configure them to do so. The deletebucket tool will fail if files are present, and you can set up a human-in-the-loop AutoGen agent to review any deletion requests before they run.

Q: How do I register the Backblaze B2 MCP Server tools with AutoGen?

You use the mcpservertools helper with your Vinkius HTTP endpoint. This automatically adapts the schemas so you can pass them directly to your AutoGen AssistantAgent.

Q: How do AutoGen agents handle failed Backblaze B2 operations?

When a tool like deletebucket returns an error, the executing agent shares the failure message with the group. The agents then debate the cause and coordinate a fix, such as clearing out remaining file versions.

Deploy AutoGen agents to debate, coordinate, and manage your Backblaze B2 buckets and file lifecycles.

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 AutoGen

Create your Vinkius account to connect Backblaze B2 to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate debates over Backblaze B2 using this MCP Server

This MCP utility exposes `create_bucket` and `update_bucket` to your AutoGen conversation, allowing different agents to negotiate storage configurations. A security agent can challenge a performance agent on ACL privacy settings before executing a change. Using a multi-agent setup ensures no bucket is provisioned with open permissions by mistake. The agents debate the configuration, reach a consensus, and only then call the tool to apply the settings.

Let AutoGen agents negotiate file deletions safely

The `hide_file` and `delete_file_version` tools allow your AutoGen agents to coordinate safe file retirements. A storage agent might propose deleting a file to save space, while an archiving agent argues to soft-delete it first using a null-marker. This multi-agent deliberation prevents accidental data loss. By requiring consensus before running a hard delete, your storage stays clean without risking active production assets.

Resolve regional data ingress routing dynamically

Your agents use `authorize_account` to dynamically discover your regional API routing endpoints during their execution planning. Before running heavy data operations, a routing agent verifies the endpoint to ensure optimal network paths. This step is handled entirely within the agent conversation. The routing agent shares the dynamic API URL with the storage manager agent, ensuring all subsequent bucket calls target the correct regional array.

Setup guide

Set up Backblaze B2 MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Backblaze B2 tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Backblaze B2_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Backblaze B2 data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Backblaze B2_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Backblaze B2 data")
    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 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 AutoGen

Only if you configure them to do so. The `delete_bucket` tool will fail if files are present, and you can set up a human-in-the-loop AutoGen agent to review any deletion requests before they run.

You use the `mcp_server_tools` helper with your Vinkius HTTP endpoint. This automatically adapts the schemas so you can pass them directly to your AutoGen AssistantAgent.

When a tool like `delete_bucket` returns an error, the executing agent shares the failure message with the group. The agents then debate the cause and coordinate a fix, such as clearing out remaining file versions.

The MCP adapter handles both stdio and streamable HTTP transports, allowing your agents to communicate with the server directly over your preferred connection.

Your bucket ACLs, file versions, and regional API endpoints are protected by Vinkius's isolated V8 sandboxing. No raw account credentials or storage configurations are ever exposed to the public model endpoints during agent conversations.

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