How to Use the Backblaze B2 MCP in LlamaIndex

Q: How does LlamaIndex handle rate limits when querying Backblaze B2?

The agent uses authorizeaccount to resolve your account's regional API endpoint, ensuring direct routing via the MCP endpoint only when needed, keeping your integration efficient.

Index your Backblaze B2 storage metadata directly into LlamaIndex vector stores for real-time, grounded RAG queries.

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 LlamaIndex

Create your Vinkius account to connect Backblaze B2 to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Backblaze B2 buckets into your LlamaIndex knowledge base

This MCP Server uses `list_buckets` and `get_file_info` to pull your actual storage architecture directly into your LlamaIndex vector index. Your query engine reads this live metadata, allowing your agent to answer questions about bucket configurations based on real data rather than guessing. By converting tool outputs into searchable document nodes, LlamaIndex ensures your agent always has the latest bucket IDs at hand. You can ask where specific assets are stored, and the agent retrieves the exact bucket partition instantly.

Map file paths and hidden files in LlamaIndex

The `list_file_names` and `hide_file` tools let your LlamaIndex RAG pipeline track which files are active and which are shadowed by null-markers. Your agent queries these file states to build an accurate semantic map of your cloud storage. This prevents your index from becoming cluttered with stale or soft-deleted files. Filtering out shadowed files ensures your search results only return active, accessible data.

Query stalled multipart uploads using semantic search

Your agent runs `list_unfinished_large_files` to feed broken upload data straight into your LlamaIndex document store. This lets you ask your agent conversational questions about which upload pipelines are failing and where your storage budget is leaking. Instead of parsing raw API logs, you query your index to find stalled chunks. The agent matches your natural language questions to the raw chunk metadata retrieved by the tool.

Setup guide

Set up Backblaze B2 MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Backblaze B2 MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Backblaze B2 tools.",
)
response = await agent.run("List recent Backblaze B2 data")

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 LlamaIndex

No, this server focuses on storage management. Your LlamaIndex agent uses tools like `list_file_names` and `get_file_info` to index metadata, file paths, and bucket configurations, not the raw binary payloads inside the files.

Install the tool spec helper, initialize the client with your Vinkius endpoint, and convert the tools using `to_tool_list_async()`. You then pass these directly to your LlamaIndex FunctionAgent.

The agent uses `authorize_account` to resolve your account's regional API endpoint, ensuring direct routing via the MCP endpoint only when needed, keeping your integration efficient.

Yes, you can use LlamaIndex's tool filtering options to restrict the agent's access, or update bucket configurations directly using the `update_bucket` tool when needed.

Yes, because all metadata queries run through an ephemeral, zero-trust V8 sandbox on the MCP host. Your bucket configurations, file paths, and upload headers are processed locally within your runtime, meaning no storage credentials or directory structures are ever cached on external servers.

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