Sample S3 MCP Server

@aws-samples

リポジトリ

基本情報

カテゴリ

ファイルとストレージ

ライセンス

MIT-0

トランスポート

stdio

作者

aws-samples

Sample S3 MCP Server について

概要はまだありません

Sample S3 MCP Server の設定

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": {
    "sample-mcp-server-s3": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Sample S3 MCP Server のツール

Returns a list of all buckets owned by the authenticated sender of the request

Returns some or all (up to 1,000) of the objects in a bucket with each request

Retrieves an object from Amazon S3. In the GetObject request, specify the full key name for the object. General purpose buckets - Both the virtual-hosted-style requests and the path-style requests are supported

概要

What is Sample S3 Model Context Protocol Server?

An MCP server implementation for retrieving data such as PDFs from AWS S3, intended for use with LLMs to load information into context.

How to use Sample S3 Model Context Protocol Server?

Obtain AWS credentials with appropriate S3 permissions, then configure the server in Claude Desktop's config file using either the development command (uv) or the published server command (uvx). The server provides tools and resources for interacting with S3 buckets and objects.

Key features of Sample S3 Model Context Protocol Server?

Exposes AWS S3 data through MCP Resources (PDF documents only, limit 1000 objects)
Provides ListBuckets tool to list all buckets owned by the authenticated sender
Provides ListObjectsV2 tool to list up to 1000 objects in a bucket
Provides GetObject tool to retrieve an object by its full key name
Supports virtual-hosted-style and path-style requests for GetObject

Use cases of Sample S3 Model Context Protocol Server?

Load PDF documents from S3 into an LLM's context for analysis
List all S3 buckets accessible to the authenticated AWS account
Retrieve specific objects from S3 by key for downstream processing
Enumerate objects in a bucket using the ListObjectsV2 tool

よくある質問

What file formats are supported?

Only PDF documents are currently supported for resource retrieval.

Is there a limit on the number of objects?

Yes, the server is limited to 1000 objects per request.

How do I authenticate with AWS?

Obtain an AWS access key ID, secret access key, and region from the AWS Management Console, and ensure the credentials have appropriate S3 permissions.

How can I debug the server?

Use the MCP Inspector by running `npx @modelcontextprotocol/inspector uv --directory <path> run s3-mcp-server`.

Where does the server configuration go?

For Claude Desktop, add the server configuration to `claude_desktop_config.json` (located in `~/Library/Application Support/Claude/` on macOS or `%APPDATA%/Claude/` on Windows).

「ファイルとストレージ」の他のコンテンツ

PDF Reader MCP Server (@shtse8/pdf-reader-mcp)

shtse8

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810