Can my AI agent debug broken uploads in Backblaze B2?

Yes. Ask your agent to list unfinished large files. It detects multipart upload shards that disconnected before completion, which consume billing quota. It provides granular visibility so you can safely clear dead streams via API.

Can the agent make my private bucket publicly accessible to serve CDN assets?

Yes. If commanded, the agent can update the bucket privacy setting from 'allPrivate' to 'allPublic'. This instantly routes objects to be fetched securely using friendly URLs for front-end hosting or CDN origins.

How does the agent handle file deletion safely using B2 protocol?

The agent can perform both soft deletes (hide file marker, triggering lifecycle purge later) or absolute hard version deletes. If you tell the agent to 'hide the file', the file remains physically safe but vanishes from directory listings.

Backblaze B2 MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Backblaze B2
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Backblaze B2 as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

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

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="backblaze_b2_agent",
    instruction=(
        "You help users interact with Backblaze B2 "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

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 Backblaze B2 MCP Server

Connect your Backblaze B2 account to any AI agent and manage your cloud storage architecture directly through natural conversation.

Google ADK natively supports Backblaze B2 as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

O que você pode fazer

Buckets — Create, delete, update privacy (allPrivate/allPublic), and list globally mapped storage buckets
File Management — Hide files (soft delete), remove explicit file versions (hard delete), and list surface names
Health Validation — List unfinished large file chunks to find failed multipart uploads
File Intelligence — Retrieve granular file details, sizes, hashes (SHA1), and content types natively

Como funciona

1. Subscribe to this server
2. Enter your Backblaze B2 Application Key ID and Key
3. Start architecting storage and debugging files from Claude, Cursor, or any MCP-compatible client

Your AI agent now has the power to orchestrate secure and cost-effective object storage without leaving your editor.

Para quem é?

DevOps Engineers — rapidly verify bucket states, clean up abandoned file versions, and debug failed multipart streams
Backend Developers — create public and private storage domains directly from development spaces
System Administrators — audit object footprint securely and perform granular file integrity checks

The Backblaze B2 MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK 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 Backblaze B2 to Google ADK via MCP

Follow these steps to integrate the Backblaze B2 MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Backblaze B2 via MCP

Why Use Google ADK with the Backblaze B2 MCP Server

Google ADK provides unique advantages when paired with Backblaze B2 through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Backblaze B2

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Backblaze B2 tools with BigQuery, Vertex AI, and Cloud Functions

Backblaze B2 + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Backblaze B2 MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Backblaze B2 and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Backblaze B2 tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Backblaze B2 regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Backblaze B2

Backblaze B2 MCP Tools for Google ADK (10)

These 10 tools become available when you connect Backblaze B2 to Google ADK via MCP:

authorize_account

Uncovers the dynamically assigned apiUrl (e.g. api003.backblazeb2.com) natively orchestrating regional data ingress specifically assigned to your billing account. Verify and extract Backblaze global session routing endpoints

create_bucket

Bootstraps essential structures before assigning automated backup syncs overriding file lock retention bounds. Provision a fresh logical Storage Bucket partition

delete_bucket

Fails intentionally via 400 Bad Request if standard files or hidden object versions persist nested inside. Ensure all lifecycle rules completed purging prior to command. Irreversibly delete an entirely empty Backblaze Storage Bucket

delete_file_version

Instantly removes the storage footprint avoiding long-term retention hoarding. Irreversibly vaporize specific absolute chunk data from disk arrays

get_file_info

Obtain granular checksum and headers associated with one precise B2 File

hide_file

Does not actually delete binary payload, merely injects a null-marker shadowing the actual file ensuring b2_list_file_names ignores it, enforcing safe soft deletion logic. Mark an active B2 file as hidden leaving data for lifecycle sweep

list_buckets

Crucial to resolve immutable String Bucket IDs prerequisite to executing downstream CRUD operations strictly inside native borders. Retrieve the exact Storage Buckets existing globally on the B2 Account

list_file_names

Examines precise .pdf, .mp4 file locations avoiding hidden shadowed states produced by lifecycle overwrite semantics. Paginate primary surface-level object metadata from a specific Bucket

list_unfinished_large_files

Crucial for verifying broken API pipelines originating from external S3 clients failing CompleteMultipartUpload. Scan B2 nodes for stalled Multipart Upload chunk aggregates

update_bucket

Use only for static asset endpoints. Mutate global ACL privacy settings for a bounded Bucket

Example Prompts for Backblaze B2 in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Backblaze B2 immediately.

"What buckets do we have enabled in Backblaze B2 right now?"

"Create a new private bucket named 'ai-crawler-logs-2026' and make it private."

"Get the file details and SHA1 for the object 'index.html' in the public bucket."

Troubleshooting Backblaze B2 MCP Server with Google ADK

Common issues when connecting Backblaze B2 to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Backblaze B2 + Google ADK FAQ

Common questions about integrating Backblaze B2 MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.