AWS S3
FreeAWS 官方示例，灵活地从 S3 获取对象（如 PDF 文档）。
FreeFree tier
About AWS S3
An AWS-sampled MCP (Model Context Protocol) server implementation that enables AI assistants like Claude to retrieve data from Amazon S3. It exposes S3 data through resources (like GET endpoints) and provides tools for listing buckets, listing objects (up to 1000 per request), and retrieving objects (currently only PDF documents). The server requires AWS credentials with appropriate S3 permissions and can be configured for use with Claude Desktop or other MCP clients. Licensed under MIT-0.
Key Features
Exposes AWS S3 data through MCP Resources (like GET endpoints)
Provides ListBuckets tool to list all buckets owned by the authenticated user
Provides ListObjectsV2 tool to list up to 1,000 objects in a bucket
Provides GetObject tool to retrieve an object from Amazon S3
Supports both virtual-hosted-style and path-style requests for general purpose buckets
Currently supports only PDF documents, limited to 1000 objects per list
MIT-0 open source license
Easy configuration with Claude Desktop via JSON config file
Pros & Cons
Pros
- Open source with permissive MIT-0 license
- Simple setup with standard AWS credentials
- Designed to work seamlessly with Claude Desktop
- Provides clear, focused S3 interaction tools
- Sample from AWS, so follows best practices
Cons
- Currently only supports PDF documents, no other file types
- Limited to 1,000 objects per ListObjectsV2 request
- Requires manual AWS credential configuration
- Primarily targeted at Claude Desktop; other MCP clients may need adaptation
- No built-in authentication or authorization beyond AWS IAM
Best For
Retrieving PDF documents from S3 for use in AI assistant contextIntegrating S3 data with Claude Desktop for document question answeringPrototyping MCP server implementations for S3 data accessBuilding applications that need to fetch S3 objects on behalf of an LLM
FAQ
What is this MCP server for?
It's an AWS sample implementation of a Model Context Protocol server that allows AI assistants to retrieve data (currently PDFs) from Amazon S3.
How do I configure it for Claude Desktop?
Add a configuration entry to your Claude Desktop config file (on MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json, on Windows: %APPDATA%/Claude/claude_desktop_config.json) with the command 'uv run s3-mcp-server' or 'uvx s3-mcp-server'.
What tools does this server provide?
It provides three tools: ListBuckets (list all S3 buckets), ListObjectsV2 (list objects up to 1,000 in a bucket), and GetObject (retrieve a specific object by bucket and key).
What types of files can it retrieve?
Currently only PDF documents are supported.
Is this server production-ready?
This is a sample server intended for demonstration and development purposes. It is not a production-ready solution.