What are the runtime dependencies?
Python 3.8 or later, plus packages `aioboto3`, `mcp[cli]`, and `python-dotenv`.
@abdullahsayyad
基本情報
A tool written in complete python following the MCP(model context protocol). LLM can leverage this tool to work with aws S3 buckets
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"AWS-S3-AccessTool": {
"command": "python",
"args": [
"C:your-absolute-path-to-the-file\\main.py"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
AWS S3 AccessTool is an MCP server utility that enables LLMs to interact with AWS S3 storage. It can list available buckets, retrieve stored objects, filter for CSV files, and read CSV content, with built-in async support via aioboto3. Developers can integrate it locally or via Docker, and it supports environment-based bucket selection.
Install dependencies: pip install aioboto3 mcp[cli] python-dotenv. Set environment variables AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION, and optionally S3_BUCKETS to restrict access. Then configure your MCP client (e.g., Cursor.ai) with the command python and the absolute path to main.py.
Python 3.8 or later, plus packages `aioboto3`, `mcp[cli]`, and `python-dotenv`.
Set the `S3_BUCKETS` environment variable to a comma-separated list of bucket names (e.g., `bucket1,bucket2`). Only those buckets will be accessible.
Use the following JSON in your MCP configuration: `{ "mcpServers": { "AWS-S3-AccessTool": { "command": "python", "args": ["C:\\your-absolute-path-to-the-file\\main.py"] } } }`
It is open-source under the MIT License.
Yes, the README mentions integration via Docker, but no specific Docker instructions are provided.

Model Context Protocol Servers
A Box model context protocol server to search, read and access files

DeviceLink lets you share folders from your computer with AI assistants, securely and in real-time. Nothing is uploaded. Your files stay on your machine, and are only accessible while the device sharing them is connected

AI tools (Claude, ChatGPT, Gemini, Grok, etc.) generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, t
MCP Server for reading many files at the same time
コメント