S3

Provides S3 file operations for MCP workflows: upload, download, list, and inspect files in an Amazon S3 bucket.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "dayongd1-mcp-s3": {
      "command": "uv",
      "args": [
        "run",
        "mcp-s3",
        "--root",
        "~/uploads"
      ],
      "env": {
        "S3_BUCKET_NAME": "your-bucket",
        "AWS_ACCESS_KEY_ID": "your_key",
        "AWS_DEFAULT_REGION": "us-east-1",
        "AWS_SECRET_ACCESS_KEY": "your_secret"
      }
    }
  }
}

You can manage files in your Amazon S3 bucket directly from any MCP-compatible client. This MCP server lets you upload, download, list, and inspect files in S3, while preserving filenames, supporting obversations like forced overwrites, and generating time-limited presigned URLs when needed. It’s ideal for AI workflows and automation where you want seamless S3 interactions from your MCP-enabled tools.

How to use

Connect your MCP client to the S3 MCP server using the local, stdio-based runtime. The server runs as a local process and you interact with it through the MCP channel defined by the runtime command. Typical actions include uploading files to your bucket, downloading files to your local workspace, listing files in the bucket, and querying file info.

How to install

Prerequisites: you need Python and the MCP runtime available in your environment. You also use the UVX/MCP runtime to launch the local server.

Configuration and usage details

Set up AWS credentials and bucket information in an environment file so your MCP client can authenticate to S3.

Security notes

Security considerations include protecting AWS credentials, using path-safe operations to avoid traversal issues, and leveraging presigned URLs with time-limited access by default to reduce exposure.

Troubleshooting

If you encounter bucket access errors, verify that your bucket name and region match your AWS configuration. If credentials are rejected, double-check that your AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY are correct and have permission to access the bucket.

Available tools

upload

Uploads a local file to S3, preserving the original filename. Supports optional force overwrite and progress tracking.

download

Downloads a file from S3 to a local path. Allows specifying destination directory.

list_files

Lists files in the configured S3 bucket, with optional filtering by prefix and limit.

get_file_info

Retrieves metadata for a specific file in S3, such as size, last modified date, and storage class.