How to Use the Backblaze B2 MCP in Vercel AI SDK

Q: How do I list files from Backblaze B2 in my Next.js app using the Vercel AI SDK?

Pass the listfilenames tool to the streamText function. The Vercel AI SDK will stream the file names from your Backblaze B2 bucket directly into your React components. You'll see the list populate in real-time.

Q: Can I create Backblaze B2 buckets directly from my UI with the Vercel AI SDK?

Yes. Your agent can call the createbucket tool. The tool returns the new bucket's ID, which you can then use to immediately list its contents or upload files.

Q: What's the point of the hidefile tool?

It's for soft deletes. hidefile marks a file as hidden without actually deleting the data, so it won't show up in listfilenames. This lets you build a "trash" or "undo" feature before permanently deleting with deletefileversion.

Build UIs that manage Backblaze B2 storage in real-time with the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Backblaze B2 to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live File Browser for B2

Connect your Next.js app to B2 and let your agent stream file lists directly into your UI. Users see objects appear as the `list_file_names` tool paginates through a bucket, with no loading spinner. You can also build an admin panel that shows broken uploads. The `list_unfinished_large_files` tool finds stalled multipart uploads, and your UI can update instantly to flag them for review.

Interactive Bucket Management

Give users the power to create and manage their own storage buckets from your app's frontend. The `create_bucket` tool provisions a new bucket, and `list_buckets` can refresh a dropdown menu with the new bucket ID, all streamed live. You can also implement a "safe delete" feature. First, use `hide_file` to mark an object for deletion, then confirm with the user before calling `delete_file_version` to permanently remove it. The UI reflects each state change as it happens.

Real-time Object Metadata with the Vercel AI SDK

Let your AI client fetch and display detailed file information on demand. When a user clicks a file in your UI, your agent calls `get_file_info` to get its checksum and headers. The results stream directly into a details panel. This gives your users immediate feedback on file integrity and properties without a full page reload, making your app feel incredibly responsive. This MCP Server makes it simple.

Setup guide

Set up Backblaze B2 MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Backblaze B2 tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Backblaze B2 transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Pass the `list_file_names` tool to the `streamText` function. The Vercel AI SDK will stream the file names from your Backblaze B2 bucket directly into your React components. You'll see the list populate in real-time.

Yes. Your agent can call the `create_bucket` tool. The tool returns the new bucket's ID, which you can then use to immediately list its contents or upload files.

Absolutely. The Vercel AI SDK is framework-agnostic. You can use this Backblaze B2 MCP Server to stream tool results into Svelte, Vue, or plain React apps just as easily as Next.js.

It's for soft deletes. `hide_file` marks a file as hidden without actually deleting the data, so it won't show up in `list_file_names`. This lets you build a "trash" or "undo" feature before permanently deleting with `delete_file_version`.

Your Vinkius endpoint token authenticates all requests. The server only touches metadata like bucket names and file info from `get_file_info`; it doesn't access or store the actual file contents. All connections are ephemeral and run in a zero-trust 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