How to Use the Backblaze B2 MCP in LangChain

Q: Can a LangChain ReAct agent delete a non-empty Backblaze B2 bucket?

No, the deletebucket tool will fail with a 400 Bad Request error if files remain. Your LangChain agent must first run a loop to hide or delete file versions before the bucket can be removed.

Q: What happens if a large upload fails mid-way?

You use listunfinishedlargefiles to find those incomplete chunks over the MCP connection. Your agent can then identify which uploads stalled and need to be cleared out to save space.

Get your LangChain agents managing Backblaze B2 buckets and tracking file versions in multi-step execution chains.

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 LangChain

Create your Vinkius account to connect Backblaze B2 to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run sequential bucket migrations in LangChain chains

This MCP Server exposes `list_buckets` and `delete_bucket` to let your LangChain agent audit and tear down empty storage structures. Your chain starts by querying your active storage partitions, evaluates which ones are empty, and immediately deletes them if they meet your cleanup criteria. Because LangChain feeds the output of one tool call directly into the next, your agent handles the entire sequence without you writing boilerplate glue code. You get full visibility of this data flow in your LangSmith traces, showing you exactly when a bucket ID passes from the list tool into the deletion tool.

Track and purge file versions inside LangGraph pipelines

The `get_file_info` and `delete_file_version` tools give your LangChain pipelines the ability to target specific chunk data on Backblaze disk arrays. Your agent inspects the file headers first to check upload timestamps, then decides whether to wipe the footprint to avoid long-term retention costs. This setup prevents your LangChain agent from making blind deletion choices. By linking these tools inside a ReAct loop, the agent verifies the target file's metadata before issuing the final delete command, keeping your storage footprint lean.

Clean up failed multipart uploads automatically

Your LangChain agent uses `list_unfinished_large_files` to identify stalled chunk aggregates from broken API uploads. When external clients fail to complete their uploads, this tool uncovers those hidden costs so your LangChain agent can flag them for removal. LangChain manages this by treating the list output as a decision prompt. The agent reads the list of stalled uploads, checks them against your retention rules, and decides whether to alert your team or trigger a cleanup sequence.

Setup guide

Set up Backblaze B2 MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Backblaze B2 tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "backblaze-b2-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Backblaze B2 transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You do not pass raw credentials to your agent. Vinkius handles the account authorization securely, exposing only the tools like `authorize_account` to your LangChain setup via the MCP protocol.

No, the `delete_bucket` tool will fail with a 400 Bad Request error if files remain. Your LangChain agent must first run a loop to hide or delete file versions before the bucket can be removed.

Every tool execution, from listing buckets to fetching file metadata, is tracked in LangSmith. You see the exact inputs, outputs, and latency for operations like `list_file_names` in real time.

You use `list_unfinished_large_files` to find those incomplete chunks over the MCP connection. Your agent can then identify which uploads stalled and need to be cleared out to save space.

Your file names, bucket IDs, and file headers never pass through third-party servers. All operations run inside an isolated V8 sandbox on Vinkius, keeping your private storage structure completely hidden from external logs.

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