Sample MCP Server S3

What is Sample MCP Server S3 about?

Provides an MCP server implementation that exposes AWS S3 data—currently PDF files—via Resources (GET‑like endpoints) and a set of helper Tools for bucket and object operations.

How to use Sample MCP Server S3?

1. Configure AWS credentials using the default profile (access‑key, secret‑key, region).
2. Install dependencies with uv sync (or pip if preferred).
3. Run the server, e.g., uv run s3-mcp-server (or uvx s3-mcp-server for a published install).
4. Add the MCP server definition to Claude Desktop’s claude_desktop_config.json under mcpServers as shown in the README.

Key features of Sample MCP Server S3

• Resources: expose up to 1,000 PDF objects per request as context for LLMs.
• Tools:
  • ListBuckets – list all buckets owned by the authenticated AWS user.
  • ListObjectsV2 – enumerate up to 1,000 objects in a bucket.
  • GetObject – retrieve any S3 object by full key name.
• Simple configuration via standard AWS credential files.
• Debuggable with the Model Context Protocol Inspector.

Use cases of Sample MCP Server S3

• Supplying large PDFs to LLMs for analysis, summarization, or Q&A.
• Enabling AI assistants to browse and fetch files stored in an organization’s S3 repository.
• Automating document retrieval workflows where AI needs direct access to cloud‑stored assets.

FAQ from the Sample MCP Server S3

Q: What file types are supported? A: Currently only PDF documents are exposed as resources; other types can be retrieved via GetObject but won’t be automatically loaded into LLM context.

Q: Is there a limit on the number of objects? A: Yes, resources are limited to 1,000 objects per request.

Q: How do I debug the server? A: Use the MCP Inspector (npx @modelcontextprotocol/inspector …) which provides a web UI for live debugging.

Q: Can I publish this server to PyPI? A: Yes, follow the build steps (uv build) and publish with uv publish after setting the appropriate PyPI token.

Sample S3 Model Context Protocol Server

An MCP server implementation for retrieving data such as PDF's from S3.

Features

Resources

Expose AWS S3 Data through Resources. (think of these sort of like GET endpoints; they are used to load information into the LLM's context). Currently only PDF documents supported and limited to 1000 objects.

Tools

• ListBuckets
  • Returns a list of all buckets owned by the authenticated sender of the request
• ListObjectsV2
  • Returns some or all (up to 1,000) of the objects in a bucket with each request
• GetObject
  • 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

Configuration

Setting up AWS Credentials

1. Obtain AWS access key ID, secret access key, and region from the AWS Management Console and configure credentials files using Default profile as shown here
2. Ensure these credentials have appropriate permission READ/WRITE permissions for S3.

Usage with Claude Desktop

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "s3-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/user/generative_ai/model_context_protocol/s3-mcp-server",
        "run",
        "s3-mcp-server"
      ]
    }
  }
}

{
  "mcpServers": {
    "s3-mcp-server": {
      "command": "uvx",
      "args": [
        "s3-mcp-server"
      ]
    }
  }
}

Development

Building and Publishing

To prepare the package for distribution:

1. Sync dependencies and update lockfile:

uv sync

2. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

3. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/user/generative_ai/model_context_protocol/s3-mcp-server run s3-mcp-server

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Security

See CONTRIBUTING for more information.

License

This library is licensed under the MIT-0 License. See the LICENSE file.