How to Use the Backblaze B2 MCP in Mastra AI

Q: How can Mastra AI handle a failed Backblaze B2 bucket deletion?

The deletebucket tool fails if the bucket isn't empty. You can build a Mastra AI workflow that first lists and deletes all file versions, then retries the deletebucket call, guaranteeing a clean removal.

Q: Can I build a scheduled task to clean up old files in Backblaze B2 with Mastra AI?

Yes. Deploy a Mastra AI agent that runs daily. It can use listfilenames to find files older than a certain date and then call deletefileversion on each one, all with automatic retries.

Q: How does Mastra AI get bucket IDs for Backblaze B2 operations?

Your agent should always call listbuckets first. This tool gets the exact bucket IDs required by other tools like listfilenames or updatebucket, preventing errors from using incorrect names.

Build unstoppable data pipelines for Backblaze B2 with Mastra AI's workflow engine.

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 Mastra AI

Create your Vinkius account to connect Backblaze B2 to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Data Cleanup Workflows

Create a Mastra AI agent that finds and cleans up stalled uploads. Your workflow can run on a schedule, call `list_unfinished_large_files`, and then conditionally decide whether to alert an admin or attempt to purge the fragments. Mastra's built-in retry logic is perfect for this. If a network blip causes a deletion to fail, it will automatically retry the `delete_file_version` call with exponential backoff, ensuring your B2 account stays clean.

Resilient Bucket Provisioning

Use a Mastra workflow to safely provision new infrastructure. The agent first calls `list_buckets` to check if a bucket with the target name already exists. If not, it proceeds to `create_bucket`. You can add a human-in-the-loop step with `requireToolApproval` before running a destructive tool like `delete_bucket`. This prevents accidental deletion of a bucket that still contains files, which would cause the tool to fail anyway.

Build Complex Backup Logic with this MCP Server

Chain together MCP tools to build sophisticated backup and archival processes. For example, a workflow could fetch data from another source, upload it, and then use `get_file_info` to confirm the checksum matches the original. If the checksum fails, Mastra's conditional branching can trigger a new upload. This lets you build truly reliable data transfer agents that manage Backblaze B2 storage without manual oversight.

Setup guide

Set up Backblaze B2 MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Backblaze B2 tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "backblaze-b2-mcp-client",
  servers: {
    "backblaze-b2-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Backblaze B2 Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Backblaze B2 tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Backblaze B2 transactions"
);
console.log(result.text);

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 Mastra AI

The `delete_bucket` tool fails if the bucket isn't empty. You can build a Mastra AI workflow that first lists and deletes all file versions, then retries the `delete_bucket` call, guaranteeing a clean removal.

Yes. Deploy a Mastra AI agent that runs daily. It can use `list_file_names` to find files older than a certain date and then call `delete_file_version` on each one, all with automatic retries.

Your agent should always call `list_buckets` first. This tool gets the exact bucket IDs required by other tools like `list_file_names` or `update_bucket`, preventing errors from using incorrect names.

It finds the specific API endpoint assigned to your B2 account. While Vinkius handles most of this, you can use it in a workflow to log the regional endpoint for diagnostics or performance tracking.

No. Your agent only interacts with file metadata—names, sizes, and checksums from tools like `get_file_info`. The Vinkius MCP server never processes or has access to the raw file content itself, and each workflow runs in its own isolated environment.

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