How to Use the Backblaze B2 MCP in Google ADK

Q: Can a Google ADK agent list files in Backblaze B2 for a BigQuery job?

Yes. The agent can use the listfilenames tool to get a file manifest from a Backblaze B2 bucket. With Gemini's long context, it can then reason about which files to include in a subsequent BigQuery data loading job.

Q: Is it possible to manage Backblaze B2 bucket permissions with a Google ADK agent?

Yes, you can change a bucket's privacy settings. The updatebucket tool allows your Google ADK agent to mutate the global ACL settings for a specific Backblaze B2 bucket, like making it public or private.

Q: What's the best tool for finding broken multipart uploads?

Use listunfinishedlargefiles. It's designed specifically to scan for incomplete large file uploads that are taking up space, which your agent can then report or act on.

Connect Gemini agents to Backblaze B2, bringing your cloud storage into your Google Cloud workflow with Google ADK.

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 Google ADK

Create your Vinkius account to connect Backblaze B2 to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Unify B2 with Google Cloud

Treat your Backblaze B2 storage like a native part of your Google Cloud environment. A Gemini agent using Google ADK can call `list_buckets` and `list_file_names` to get a full inventory of your B2 assets. It can hold that entire file list in its massive context window to decide which data to pull for a BigQuery job. This isn't just about listing files. Your agent can reason about the data it sees in B2 and then trigger a Vertex AI pipeline to process it. It connects your B2 data directly to your Google-based AI and data workflows.

Enterprise-Scale B2 Management

Orchestrate your Backblaze B2 infrastructure from a central agent built on Google ADK. Your agent can provision new storage for a project with `create_bucket` or change access policies on an existing bucket with `update_bucket`. You manage B2 with the same agent that manages your GCS and BigQuery resources. This MCP Server exposes the core B2 functions your enterprise agent needs. You can build automated workflows that span multiple clouds, all controlled by a single agent running on Google's infrastructure.

Audit Storage & Clean Up Stalled Uploads

Put a Gemini agent in charge of keeping your B2 account clean. It can use `list_unfinished_large_files` to scan for stalled multipart uploads—a common problem with API-driven uploads—and log them for review. This is perfect for maintaining data hygiene at scale. For compliance, your agent can also manage data retention. It can use `delete_file_version` to remove specific object versions that are past their required retention date. The agent's actions can be logged directly to Google Cloud Logging for a complete audit trail.

Setup guide

Set up Backblaze B2 MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Backblaze B2 tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Backblaze B2_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Backblaze B2 tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Yes. The agent can use the `list_file_names` tool to get a file manifest from a Backblaze B2 bucket. With Gemini's long context, it can then reason about which files to include in a subsequent BigQuery data loading job.

Vinkius handles it. You connect your Google ADK agent to the MCP Server endpoint with a single token. The server manages the connection to the Backblaze B2 API securely.

Yes, you can change a bucket's privacy settings. The `update_bucket` tool allows your Google ADK agent to mutate the global ACL settings for a specific Backblaze B2 bucket, like making it public or private.

Use `list_unfinished_large_files`. It's designed specifically to scan for incomplete large file uploads that are taking up space, which your agent can then report or act on.

The server only interacts with your Backblaze B2 metadata. This includes bucket lists, file names, object headers, and information about unfinished uploads. Your B2 account credentials and the file data itself are never touched or stored by the Vinkius platform.

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