AWS MCP Server

What is AWS MCP Server about?

AWS MCP Server implements Model Context Protocol operations for Amazon Web Services, currently supporting S3 bucket/object management and DynamoDB table/item manipulation. All actions are recorded and can be reviewed through a dedicated audit resource.

How to use AWS MCP Server?

1. Install via Smithery (recommended):

   npx -y @smithery/cli install mcp-server-aws --client claude
   

2. Manual setup:
   • Clone the repository.
   • Provide AWS credentials through environment variables (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION) or the default AWS CLI credential chain.
   • Add a server entry to claude_desktop_config.json pointing to the repository and using uv run mcp-server-aws.
   • Launch Claude Desktop and invoke any of the provided tools (e.g., s3_bucket_create, dynamodb_item_put).

Key Features of AWS MCP Server

• S3 Operations: create, list, delete buckets; upload, read, list, delete objects.
• DynamoDB Operations: create, describe, delete, update tables; full CRUD for items; batch get/write; PartiQL batch execution; TTL management.
• Automatic Auditing: every operation is logged and accessible via audit://aws-operations.
• Claude Integration: usable directly from the Claude desktop app as an MCP server.
• Simple Installation: one‑click install through Smithery or manual setup with minimal configuration.

Use Cases of AWS MCP Server

• Automating cloud resource provisioning during AI‑driven workflows.
• Allowing Claude to read/write data to S3/DynamoDB without exposing raw AWS credentials to the user.
• Auditable data manipulation for compliance or debugging.
• Rapid prototyping of serverless back‑ends driven by natural language commands.

FAQ from the AWS MCP Server

Q: Which AWS services are supported? A: Currently S3 and DynamoDB. Additional services may be added in future releases.

Q: Do I need special IAM permissions? A: Yes, an IAM user with read/write permissions for S3 and DynamoDB in your account.

Q: How are operations logged? A: Every request is recorded and can be retrieved via the audit://aws-operations endpoint.

Q: Can I run the server on Windows? A: Yes. Follow the manual installation steps and update the path to claude_desktop_config.json accordingly.

Q: What if I encounter credential errors? A: Verify that AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and optionally AWS_REGION are correctly set, or use aws configure to set up the default credential chain.

AWS MCP Server

A Model Context Protocol server implementation for AWS operations that currently supports S3 and DynamoDB services. All operations are automatically logged and can be accessed through the audit://aws-operations resource endpoint.

See a demo video here.

Listed as a Community Server within the MCP servers repository.

Running locally with the Claude desktop app

Installing via Smithery

To install AWS MCP Server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-server-aws --client claude

Manual Installation

1. Clone this repository.
2. Set up your AWS credentials via one of the two methods below. Note that this server requires an IAM user with RW permissions for your AWS account for S3 and DynamoDB.

• Environment variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_REGION (defaults to us-east-1)
• Default AWS credential chain (set up via AWS CLI with aws configure)

3. Add the following to your claude_desktop_config.json file:

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

"mcpServers": {
  "mcp-server-aws": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/repo/mcp-server-aws",
      "run",
      "mcp-server-aws"
    ]
  }
}

4. Install and open the Claude desktop app.
5. Try asking Claude to do a read/write operation of some sort to confirm the setup (e.g. create an S3 bucket and give it a random name). If there are issues, use the Debugging tools provided in the MCP documentation here.

Available Tools

S3 Operations

• s3_bucket_create: Create a new S3 bucket
• s3_bucket_list: List all S3 buckets
• s3_bucket_delete: Delete an S3 bucket
• s3_object_upload: Upload an object to S3
• s3_object_delete: Delete an object from S3
• s3_object_list: List objects in an S3 bucket
• s3_object_read: Read an object's content from S3

DynamoDB Operations

Table Operations

• dynamodb_table_create: Create a new DynamoDB table
• dynamodb_table_describe: Get details about a DynamoDB table
• dynamodb_table_delete: Delete a DynamoDB table
• dynamodb_table_update: Update a DynamoDB table

Item Operations

• dynamodb_item_put: Put an item into a DynamoDB table
• dynamodb_item_get: Get an item from a DynamoDB table
• dynamodb_item_update: Update an item in a DynamoDB table
• dynamodb_item_delete: Delete an item from a DynamoDB table
• dynamodb_item_query: Query items in a DynamoDB table
• dynamodb_item_scan: Scan items in a DynamoDB table

Batch Operations

• dynamodb_batch_get: Batch get multiple items from DynamoDB tables
• dynamodb_item_batch_write: Batch write operations (put/delete) for DynamoDB items
• dynamodb_batch_execute: Execute multiple PartiQL statements in a batch

TTL Operations

• dynamodb_describe_ttl: Get the TTL settings for a table
• dynamodb_update_ttl: Update the TTL settings for a table