MCP For Claude Marketplace
Backblaze B2

Backblaze B2 MCP Connector for Claude

A+

Manage Backblaze B2 Cloud Storage via AI — control buckets, file versions, objects, and access rules autonomously.

10 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

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

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
s3-compatibleobject-storagefile-managementdata-archivingbucket-managementcloud-backup

10 tools expose this connector's capabilities to your AI agent.

get_file_info

Obtain granular checksum and headers associated with one precise B2 File

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

create_bucket

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

delete_file_version

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

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

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 globalThis session routing endpoints

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

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 globalThis ACL privacy settings for a bounded Bucket

See how to talk to your AI agent using Backblaze B2.

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

You have 3 active storage buckets: `production-assets-22` (allPublic), `backup-logs-internal` (allPrivate), and `db-dumps` (allPrivate). Should I query the unfinished large files stream to check for ghost chunks on the database dumps bucket?

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

The bucket `ai-crawler-logs-2026` has been successfully created and partitioned via the Backblaze B2 node. Its status is strictly set to `allPrivate` preventing public reads.

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

File Details for `index.html`: The file uses `text/html`, is 34.2 KB globally, with an active unique ID of 4_zX... and the explicitly computed SHA1 trace is `2f8bX...`. It is fully accessible via the B2 friendly download URL.

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.

Related Connectors

Notesnook (Private Note Taking & E2EE)

Notesnook (Private Note Taking & E2EE) MCP

12 tools Official

Manage encrypted notes via Notesnook — create secure entries, sync your vault, and audit private notebooks.

A+ View details →
Azure Cognitive Search

Azure Cognitive Search MCP

7 tools

Empower your AI with enterprise retrieval — run full-text search, semantic queries, and inspect cognitive skillsets on your Azure indexes.

A+ View details →
NEW
Backup Storage Capacity Forecast

Backup Storage Capacity Forecast MCP

4 tools Official

Predict backup storage consumption, exhaustion timelines, and required expansions.

A+ View details →
NEW
Family Photo Counter

Family Photo Counter MCP

4 tools Official

Count photos across nested family photo albums.

A+ View details →