How to Use the Backblaze B2 MCP in CrewAI

Q: How can a CrewAI team safely delete a Backblaze B2 bucket?

Assign one agent to list and delete all file versions with deletefileversion. Once it confirms the bucket is empty, it signals a second agent to execute the final deletebucket command. This separation of concerns prevents errors.

Q: Can I use CrewAI to monitor my Backblaze B2 account for security issues?

Definitely. Have a 'Security' agent run listbuckets and updatebucket in a read-only or check mode. If it finds a bucket with public ACLs that shouldn't have them, it can alert a human or another agent to correct it.

Deploy an autonomous crew of AI agents to manage your Backblaze B2 cloud storage with CrewAI.

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 CrewAI

Create your Vinkius account to connect Backblaze B2 to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Storage Auditor Crew

Assign a 'Monitor' agent to periodically scan your account with `list_unfinished_large_files` and `list_buckets`. This agent's only job is to watch for problems, like stalled uploads or buckets with insecure ACLs. When the Monitor finds an issue, it passes the details to a 'Janitor' agent. The Janitor agent then takes action, using tools like `delete_file_version` to clean up fragments or `update_bucket` to fix permissions. This is how you build a self-healing storage system.

Role-Based Data Lifecycle Management

Create an 'Archivist' agent that uses `list_file_names` to identify files ready for archival. Instead of deleting them, it can use `hide_file` to take them out of active rotation, passing a list to a 'Deletion' agent. The Deletion agent, operating on a delay, then works through the list, using `delete_file_version` to permanently purge the data. This specialization prevents a single agent from accidentally deleting critical data. This MCP Server gives them the tools they need.

Smart Provisioning with a CrewAI Team

Task a 'Planner' agent to decide when a new bucket is needed. It uses `list_buckets` to check the current state. Once it decides, it delegates the task to a 'Provisioner' agent. The Provisioner agent's sole responsibility is to execute the `create_bucket` tool and then use `update_bucket` to set the correct access policies. This division of labor makes your autonomous operations more reliable and easier to debug.

Setup guide

Set up Backblaze B2 MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Backblaze B2 tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Backblaze B2 Analyst",
    goal="Access and analyze Backblaze B2 data via MCP.",
    backstory="Expert analyst with direct Backblaze B2 access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Backblaze B2 transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Backblaze B2 Analyst",
        goal="Access and analyze Backblaze B2 data via MCP.",
        backstory="Expert analyst with direct Backblaze B2 access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Backblaze B2 transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Assign one agent to list and delete all file versions with `delete_file_version`. Once it confirms the bucket is empty, it signals a second agent to execute the final `delete_bucket` command. This separation of concerns prevents errors.

Definitely. Have a 'Security' agent run `list_buckets` and `update_bucket` in a read-only or check mode. If it finds a bucket with public ACLs that shouldn't have them, it can alert a human or another agent to correct it.

An 'Uploader' agent could handle the transfer. A 'Verifier' agent could then use `get_file_info` to check the file's checksum against the source. If it fails, the Verifier can delegate back to the Uploader to try again.

The easiest way is to pass the Vinkius MCP endpoint URL directly into the agent's `mcps` parameter. For more control, use `MCPServerHTTP` and a `tool_filter` to give each agent in your crew access to only the specific tools its role requires.

The agents interact strictly with metadata: bucket names from `list_buckets`, file names from `list_file_names`, and file headers from `get_file_info`. The actual contents of your files are never touched or seen by the Vinkius server or the agents. All operations are secured via your token and executed in an ephemeral sandbox.

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