Can Cloudflare's server read or write individual objects in R2?

Not through the tools exposed here. r2_buckets_list and r2_bucket_create operate at the bucket level. For object-level operations like reading, writing, or presigning, MinIO (our top pick) or AWS (AWS Labs) via the AWS CLI are the stronger fits.

When is Cloudflare the right object-storage pick?

When your buckets are R2 on Cloudflare's edge and the agent needs bucket-level management (r2_buckets_list, r2_bucket_create), especially if it also touches Workers or KV through the same server. For a fuller object surface, MinIO ranks first here.

Cloudflare for object storage

Pick 3 of 3 for object storageOfficialCloudflare3,806

Object storage is where apps keep their bytes: uploads, artifacts, checkpoints, log archives, static assets. Cloudflare's remote servers manage R2 buckets alongside Workers, KV, and D1, and for object storage it is our third pick of three: the right call specifically when your buckets live on Cloudflare's edge, and a narrower fit than the two siblings otherwise.

The honest framing is reach. Through the tools exposed here, Cloudflare handles R2 at the bucket level rather than the full per-object surface. That places it third on this list, while remaining the obvious choice if R2 is already where your bytes sit.

How Cloudflare fits

For object storage, the relevant tools are r2_buckets_list and r2_bucket_create, scoped by accounts_list and set_active_account. An agent can enumerate the R2 buckets in an account and create new ones, with the rest of the server (Workers and KV tools like workers_list and kv_namespaces_list) available if the same agent also touches edge compute or key-value state.

The limit is granularity. These tools operate at the bucket level; there is no tool here to list or read individual objects, write a blob, generate a presigned URL, or inspect lifecycle and versioning. MinIO, our top pick, is the self-hostable S3-compatible engine with a fuller object surface, and AWS (AWS Labs) reaches S3's object-level operations through the broad AWS CLI. Choose Cloudflare when your object storage is R2 on the edge and bucket-level management is what the agent needs; reach for a sibling when it must work with individual objects.

Tools you would use

Tool	What it does
accounts_list	List all accounts in your Cloudflare account.
set_active_account	Set the active account used for tool calls that require an account ID.
kv_namespaces_list	List the Workers KV namespaces in your account.
kv_namespace_create	Create a new Workers KV namespace.
kv_namespace_delete	Delete a Workers KV namespace.
kv_namespace_get	Get the details of a Workers KV namespace.
kv_namespace_update	Update the title of a Workers KV namespace.
workers_list	List the Workers deployed in your account.
workers_get_worker	Get the details of a Cloudflare Worker.
workers_get_worker_code	Get the source code of a Cloudflare Worker (may be the bundled version).

Full Cloudflare setup and config →

FAQ

Can Cloudflare's server read or write individual objects in R2?: Not through the tools exposed here. r2_buckets_list and r2_bucket_create operate at the bucket level. For object-level operations like reading, writing, or presigning, MinIO (our top pick) or AWS (AWS Labs) via the AWS CLI are the stronger fits.
When is Cloudflare the right object-storage pick?: When your buckets are R2 on Cloudflare's edge and the agent needs bucket-level management (r2_buckets_list, r2_bucket_create), especially if it also touches Workers or KV through the same server. For a fuller object surface, MinIO ranks first here.