AWS S3 MCP Server
Enables interaction with AWS S3 storage through bucket operations (create, delete, list), object management (upload, download, delete, list), and bucket policy configuration using AWS credentials.
README
AWS S3 MCP Server
A Model Context Protocol (MCP) server for AWS S3 operations
Features
This MCP server provides tools for interacting with AWS S3:
Bucket Operations
list_buckets- List all S3 buckets in the AWS accountcreate_bucket- Create a new S3 bucketdelete_bucket- Delete an S3 bucket (must be empty)
Object Operations
list_objects- List objects in a bucket with optional prefix filteringupload_object- Upload a file or content to a bucketdownload_object- Download an object from a bucketdelete_object- Delete an object from a bucket
Policy Operations
get_bucket_policy- Get the policy attached to a bucketset_bucket_policy- Set or update a bucket policy
MCP Configuration
Create a configuration file for the MCP server:
{
"mcpServers": {
"aws-s3": {
"command": "npx",
"args": ["aws-s3"],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "your-access-key-id",
"AWS_SECRET_ACCESS_KEY": "your-secret-access-key"
},
"autoApprove": ["list_buckets", "list_objects", "get_bucket_policy"]
}
}
}
Available Tools
The MCP server provides the following tools:
| Tool Name | Description | Parameters |
|---|---|---|
list_buckets |
Lists all S3 buckets in the AWS account | None |
create_bucket |
Creates a new S3 bucket | bucketName (required), region (optional) |
delete_bucket |
Deletes an empty S3 bucket | bucketName (required) |
list_objects |
Lists objects in a bucket | bucketName (required), prefix, maxKeys, continuationToken (all optional) |
upload_object |
Uploads a file or content to a bucket | bucketName, key (both required), filePath, content, contentType (all optional) |
download_object |
Downloads an object from a bucket | bucketName, key (both required), outputPath, returnContent (both optional) |
delete_object |
Deletes an object from a bucket | bucketName, key (both required) |
get_bucket_policy |
Gets the policy for a bucket | bucketName (required) |
set_bucket_policy |
Sets or updates a bucket policy | bucketName, policy (both required) |
AWS Authentication
The MCP server uses the AWS SDK, which looks for credentials in the following order:
- Environment variables (
AWS_ACCESS_KEY_IDandAWS_SECRET_ACCESS_KEY) - Shared credentials file (
~/.aws/credentials) - If running on Amazon EC2, EC2 instance metadata service
For local development, you can:
- Set environment variables in your MCP server configuration
- Configure the AWS CLI with
aws configure - Use AWS IAM roles if running in an AWS environment
Tool Documentation
list_buckets
Lists all S3 buckets in the AWS account.
Parameters: None
Response:
{
"success": true,
"buckets": [
{
"name": "my-bucket",
"creationDate": "2023-01-15T00:00:00.000Z"
}
],
"count": 1
}
create_bucket
Creates a new S3 bucket with the specified name.
Parameters:
bucketName(string, required): Name of the bucket to createregion(string, optional): AWS region where the bucket should be created
Response:
{
"success": true,
"bucketName": "my-new-bucket",
"location": "http://my-new-bucket.s3.amazonaws.com/"
}
delete_bucket
Deletes an S3 bucket. The bucket must be empty.
Parameters:
bucketName(string, required): Name of the bucket to delete
Response:
{
"success": true,
"bucketName": "my-bucket"
}
list_objects
Lists objects in an S3 bucket with optional prefix filtering.
Parameters:
bucketName(string, required): Name of the bucket to list objects fromprefix(string, optional): Filter objects by prefix (folder path)maxKeys(number, optional): Maximum number of objects to return (default: 1000)continuationToken(string, optional): Token to retrieve the next set of results
Response:
{
"success": true,
"objects": [
{
"key": "folder/file.txt",
"size": 1024,
"lastModified": "2023-01-15T00:00:00.000Z",
"etag": "\"abc123\"",
"storageClass": "STANDARD"
}
],
"count": 1,
"isTruncated": false
}
upload_object
Uploads a file or content to an S3 bucket.
Parameters:
bucketName(string, required): Name of the bucket to upload tokey(string, required): Object key (path) in the bucketfilePath(string, optional): Local file path to uploadcontent(string, optional): String content to uploadcontentType(string, optional): MIME type of the content
Response:
{
"success": true,
"bucketName": "my-bucket",
"key": "folder/file.txt",
"etag": "\"abc123\""
}
download_object
Downloads an object from an S3 bucket.
Parameters:
bucketName(string, required): Name of the bucket to download fromkey(string, required): Object key (path) in the bucketoutputPath(string, optional): Local file path to save the downloaded objectreturnContent(boolean, optional): If true, returns the object content in the response
Response:
{
"success": true,
"bucketName": "my-bucket",
"key": "folder/file.txt",
"outputPath": "/local/path/file.txt",
"content": "File content if returnContent is true",
"contentType": "text/plain",
"size": 1024
}
delete_object
Deletes an object from an S3 bucket.
Parameters:
bucketName(string, required): Name of the bucket containing the objectkey(string, required): Object key (path) to delete
Response:
{
"success": true,
"bucketName": "my-bucket",
"key": "folder/file.txt"
}
get_bucket_policy
Retrieves the policy for an S3 bucket.
Parameters:
bucketName(string, required): Name of the bucket to get the policy for
Response:
{
"success": true,
"bucketName": "my-bucket",
"policy": {
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Principal": "*",
"Action": "s3:GetObject",
"Resource": "arn:aws:s3:::my-bucket/*"
}
]
}
}
set_bucket_policy
Sets or updates the policy for an S3 bucket.
Parameters:
bucketName(string, required): Name of the bucket to set the policy forpolicy(string or object, required): The policy document as a JSON string or object
Response:
{
"success": true,
"bucketName": "my-bucket"
}
License
This project is licensed under the MIT License - see the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.