list-s3-bucketsLABSCO SUMMARY
One call: which buckets can this account see?
That is the whole surface. It answers the orientation question at the start of an S3 task and nothing past it — no objects, no reads of content, no writes.
What it is
A single read call over AWS S3: the buckets your configured credentials can reach, optionally scoped to one region.
What you get
- Every S3 bucket your AWS credentials can reach, as a formatted list
- The same list narrowed to a region you name
Requirements
Python 3.13 or newer and uv, plus AWS credentials already configured — an aws configure profile, environment variables, or an IAM role if you are running on AWS.
Setup effort
Build from source — git clone https://github.com/sofianhamiti/mcp-server-s3.git
USE CASES
01
Getting your bearings in an unfamiliar AWS account
The bucket list is the first thing anyone asks for, and it arrives without a console login or a CLI switch.
02
Confirming what a set of credentials actually reaches
The returned list is exactly what the configured identity is allowed to see, which is a faster answer than reading the policy.
03
Checking a bucket landed in the region you meant
Pass the region and see whether it is there, instead of assuming the default picked correctly.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation. list-s3-buckets only lists bucket names, with an optional region; no other S3 operations are available.
Requires
- Python 3.13 or later
- uv
- AWS credentials — an aws configure profile, AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY in your environment, or an IAM role when running on AWS
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/sofianhamiti/mcp-server-s3.git
cd mcp-server-s3
uv syncMCP Clients
Claude Desktop — local build
CLAUDE DESKTOP — LOCAL BUILD · JSON
{
"mcpServers": {
"s3-tools": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_SERVER_S3>",
"run",
"s3-tools"
]
}
}
}
