Backblaze B2 MCP. Audit object states and manage cloud data lifecycle.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Backblaze B2 MCP manages your entire cloud storage architecture through natural conversation. Use this to create, delete, and audit buckets; track file versions for compliance; or pinpoint stalled large uploads—all without leaving your editor.
What your AI agents can do
Authorize account
Verifies and extracts the correct global session routing endpoints for your B2 billing account.
Create bucket
Provisions a fresh, logically partitioned storage bucket structure.
Delete bucket
Irreversibly deletes an entire empty Backblaze Storage Bucket partition after ensuring all lifecycle rules are complete.
Create new, isolated storage buckets with specific public or private access rules.
Get granular details for any file, including its unique ID, size, and cryptographic hash (SHA1).
Soft-delete files by marking them as hidden without losing the underlying data payload.
Irreversibly delete specific versions of a file or entire buckets to prevent retention hoarding.
Scan the B2 system for incomplete large file chunks, useful when debugging external data pipelines.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Backblaze B2: 10 Tools for Object Storage Control
These ten tools give your agent full command over every aspect of your Backblaze B2 account, from creating buckets to auditing file chunks.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Backblaze B2 on Vinkius019d7557authorize account
Verifies and extracts the correct global session routing endpoints for your B2 billing account.
019d7557create bucket
Provisions a fresh, logically partitioned storage bucket structure.
019d7557delete bucket
Irreversibly deletes an entire empty Backblaze Storage Bucket partition after ensuring all lifecycle rules are complete.
019d7557delete file version
Instantly vaporizes a specific chunk of data, removing the storage footprint completely.
019d7557get file info
Retrieves granular headers and checksums for one precise file within B2.
019d7557hide file
Marks an active file as hidden, effectively performing a safe soft deletion that keeps the data available for later cleanup.
019d7557list buckets
Retrieves the exact list of all global Storage Buckets existing on your B2 account.
019d7557list file names
Pages primary object metadata, showing file locations from a specific bucket while avoiding hidden states.
019d7557list unfinished large files
Scans B2 nodes to identify and report on stalled multipart upload chunk aggregates.
019d7557update bucket
Modifies global access control list (ACL) privacy settings for a specific storage bucket.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Backblaze B2, then connect any of our 4,800+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,800+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Dealing with forgotten and orphaned file versions is a huge headache.
Right now, if you're cleaning up an active storage environment, you have to manually check multiple consoles. You look at the bucket list, then drill down into individual files to see what versions exist, and finally run separate commands just to find those unfinished large file uploads that are consuming space but nobody remembers about.
With this MCP, your agent handles all of that overhead in one go. You can tell it to scan for stalled chunks with `list_unfinished_large_files` or audit the full set of containers using `list_buckets`. The result is a clean report detailing exactly what's active and what needs attention.
The `delete_file_version` tool gives you total control over data history.
Before, deleting old versions felt risky. You were worried about hitting a live file or accidentally wiping the wrong historical snapshot because the console didn't give enough detail on what was truly being targeted. It was always guesswork.
Now, you have precise control. You use `delete_file_version` to irretrievably vaporize specific data chunks by their version ID. This means you target exactly what needs clearing without risking any live assets.
What you can do with this MCP connector
Need to manage complex object storage? This connection lets you treat Backblaze B2 like a direct extension of your AI agent. Instead of logging into a console and clicking through dozens of tabs, you simply ask what needs doing. You can provision new private buckets, track every file version for audit purposes, or find those tricky incomplete uploads that are chewing up space.
The platform runs every action inside its own V8 isolate sandbox with 34+ security rules enforced on every single call. This means when your agent handles sensitive keys—like your B2 credentials—they pass through a zero-trust proxy. Your keys never sit on a disk. You connect once from any MCP-compatible client and gain total control over object lifecycle, making sure your data stays secure and properly organized.
019d7557-f367-7302-9200-58f220cb6eb8 
How Backblaze B2 MCP Works
- 1 Subscribe to this MCP and provide your Backblaze B2 Application Key ID and Key.
- 2 Connect your preferred AI client (Claude, Cursor, etc.) to the Vinkius platform.
- 3 Ask your agent to perform a task, like listing existing buckets or getting file details. The operation runs right where you are.
The bottom line is: your agent handles complex cloud operations using simple conversation.
Who Is Backblaze B2 MCP For?
Anyone who deals with large volumes of structured, archived data. The Ops Engineer tired of manually checking logs for failed multipart uploads; the Backend Developer needing to spin up a new private asset domain on demand.
Using this MCP to rapidly verify bucket states, clean up abandoned file versions, and debug broken data streams.
Creating public or private storage domains directly from development spaces as part of a feature rollout.
Auditing object footprints to ensure compliance and performing granular integrity checks across the entire cloud setup.
What Changes When You Connect
- Stop manually checking for failed uploads. Use
list_unfinished_large_filesto scan B2 nodes for stalled multipart upload chunks, diagnosing broken API pipelines immediately. - Never lose an audit trail again. Get granular file details with
get_file_info, retrieving the SHA1 checksum and content type right from your editor. - Need a new storage domain? Use
create_bucketto provision a fresh logical bucket partition in seconds, setting precise public or private rules instantly. - Keep your asset list clean. Instead of manually purging data, use
hide_filefor soft deletion, which marks the file while leaving it ready for lifecycle sweep. - Need to change permissions? Run
update_bucketto mutate global ACL privacy settings on a bucket without touching any code or infrastructure scripts.
Real-World Use Cases
Debugging failed data uploads
A client's external upload pipeline fails halfway through. Instead of checking logs across multiple systems, the agent runs list_unfinished_large_files, instantly pointing to the specific stalled chunk aggregate that needs fixing.
Setting up a new internal log archive
A team needs dedicated space for compliance logs. The user asks the agent to run create_bucket with strict allPrivate rules, provisioning and partitioning the storage bucket instantly.
Auditing sensitive data before deletion
Before decommissioning an old dataset, the administrator runs list_buckets to see all containers, then uses get_file_info on key files to verify their hashes and contents.
The Tradeoffs
Trying to delete everything at once
The user tries to run a single command to clear out all old versions of a file, risking accidental data loss or hitting an API error because some files are still in use.
→
Use list_file_names first to map the contents. Then, specifically target only the outdated chunks using delete_file_version. This precise approach avoids unintended deletion.
Mistaking listing names for metadata
The user relies only on basic file listings and misses crucial security data like the object's MIME type or its unique ID.
→
Always call get_file_info when you need certainty. This tool provides granular details, including the SHA1 hash and content type, giving you full confidence in the metadata.
When It Fits, When It Doesn't
Use this MCP if your workflow requires deep control over object lifecycle management—think archiving, compliance auditing, or debugging massive data pipelines. You need to know not just that a file exists, but its exact hash, who owns it, and if any chunks are incomplete.
Don't use this if you simply need basic file sharing or collaboration; those services handle the basics. If your problem is merely 'where did I save that photo?', you only need simple listing capabilities. This MCP steps in when you need to govern access rules via update_bucket or surgically remove old data using delete_file_version, going far beyond standard cloud GUI features.
Common Questions About Backblaze B2 MCP
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.
What is the first step when using `authorize_account` for Backblaze B2? +
The tool extracts your specific global session routing endpoint. This verifies and reveals the dynamically assigned API URL needed for your region or billing account, ensuring subsequent calls target the correct node.
Does using `list_file_names` bypass hidden or soft-deleted objects? +
Yes, it only pulls primary surface-level object metadata. This method is specifically designed to paginate names from a bucket while ignoring any files marked as hidden or shadowed by lifecycle rules.
Can I get checksum and headers using `get_file_info` for an object? +
Absolutely. The tool obtains granular metadata, including the SHA1 hash and content type, without needing to download the actual file payload. This lets you audit integrity before making any changes.
What conditions must be met before running `delete_bucket`? +
You must confirm the bucket is entirely empty. The command will intentionally fail with a Bad Request error if any files, hidden versions, or objects remain inside the partition.
What is the function of the `hide_file` tool compared to actual deletion? +
This method doesn't delete the binary payload; it simply injects a null-marker. This effectively soft deletes the file, making it invisible to standard listings while preserving all data for later recovery or lifecycle sweeps.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.