{"id":113380,"date":"2026-09-08T11:13:00","date_gmt":"2026-09-08T18:13:00","guid":{"rendered":"https:\/\/www.backblaze.com\/blog\/?p=113380"},"modified":"2026-09-08T11:13:03","modified_gmt":"2026-09-08T18:13:03","slug":"introducing-the-backblaze-b2-mcp-server","status":"publish","type":"post","link":"https:\/\/www.backblaze.com\/blog\/introducing-the-backblaze-b2-mcp-server\/","title":{"rendered":"Introducing the Backblaze B2 MCP Server"},"content":{"rendered":"\n
\"An<\/figure>\n\n\n\n
<\/div>\n\n\n\n

AI agents are getting very good at making things: reports, code builds, images, videos, datasets, customer exports, and backups. But generating a file is only half the job. The agent still needs somewhere durable to put it. That\u2019s where B2 comes in.<\/p>\n\n\n\n

Today, we’re introducing the Backblaze B2 MCP Server<\/a>: an open source server that gives AI agents a safe, standard way to operate cloud object storage.<\/p>\n\n\n\n

Introducing the Backblaze B2 MCP Server<\/h2>\n\n\n\n

Model Context Protocol (MCP) provides a common way for AI agents to discover and use external tools. The Backblaze B2 MCP Server applies that model to Backblaze B2 Cloud Storage, connecting MCP-compatible clients to a focused set of storage operations.<\/p>\n\n\n\n

The server is open source and designed so the tools presented to the agent reflect the permissions of the connected B2 application key.<\/p>\n\n\n\n

And that last point is important. The MCP server does not invent a new permission model or grant an agent blanket access to your account. If the key can only read from one bucket, the agent’s usable tool set and reach are constrained accordingly. If the key does not permit an operation, the agent cannot use the MCP server to bypass that boundary.<\/p>\n\n\n\n

Why launch an MCP server?<\/h2>\n\n\n\n

Storage has always met developers in two places: the API and the console. Agent tools are becoming a third, and increasingly the one where work starts. Our view is that infrastructure should be available inside the tool someone already has open, at the moment they need it.<\/p>\n\n\n\n

That spans a wide range of work: everyday tasks that produce outputs which need to be stored, AI workflows that read and write data as they run, and applications that require storage to handle files. A report or an export has to land somewhere durable. An application built around agents needs somewhere to put user uploads, generated assets, and datasets. Customers have also asked us how their own agents can administer their storage.<\/p>\n\n\n\n

MCP is what lets one implementation serve all of it. An MCP server provides these storage tools directly to the AI agents people use for everyday tasks and for coding, so the same credentials, scoping, transfer path, and destructive operation policy apply everywhere your team works. B2 is available inside the tools your teams already have open.<\/p>\n\n\n\n

See it in action<\/h2>\n\n\n\n

Suppose an agent has prepared a customer export. Instead of handing it a general-purpose credential and writing the surrounding storage logic yourself, you could ask:<\/p>\n\n\n\n

“Prepare a private destination for this customer export. Keep it for 30 days and give me a secure way to upload it.”<\/p>\n\n\n\n

Depending on the application key\u2019s permissions and the server\u2019s policy settings, the agent can:<\/p>\n\n\n\n

    \n
  1. Create a private bucket or select an existing one the key can access.<\/li>\n\n\n\n
  2. Apply lifecycle or retention settings, depending on whether the export should expire automatically or be protected from deletion.<\/li>\n\n\n\n
  3. Generate a short-lived upload URL.<\/li>\n\n\n\n
  4. Verify that the export arrived.<\/li>\n\n\n\n
  5. Return a short-lived download URL to the intended recipient.<\/li>\n<\/ol>\n\n\n\n

    For a large export, the bytes move directly to B2 using the short-lived URL; they do not need to pass through the model conversation or the MCP server. That keeps bulk data on the right path and leaves the agent responsible for orchestrating the work, not hauling the payload.<\/p>\n\n\n\n

    Now imagine a follow-up request: “Delete that export.” The B2 MCP Server can require confirmation before the action proceeds or block destructive operations entirely, depending on how the server is configured. The same principle applies to changes that weaken protection, such as clearing retention or introducing lifecycle rules that schedule deletion.<\/p>\n\n\n\n

    The result is a useful division of labor: The agent can set up the storage, move the file, and verify the outcome, while the B2 MCP server enforces the connected key\u2019s limits and configured policy.<\/p>\n\n\n\n

    Built for real storage work<\/h2>\n\n\n\n

    The B2 MCP Server includes up to 40 tools across the B2 Native API, B2’s S3 Compatible API, and purpose-built storage analytics. You do not need to expose all of them to every agent. The available surface adjusts to the connected key and the server’s policy settings.<\/p>\n\n\n\n