AWS Resources
A Python-based MCP server that lets Claude run boto3 code to query and manage AWS resources. Execute powerful AWS operations directly through Claude with proper sandboxing and containerization. No need for complex setups - just pass your AWS credenti
What is AWS Resources?
AWS Resources is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to python-based mcp server that lets claude run boto3 code to query and manage aws resources. execute powerful aws operations directly through claude with proper sandboxing and containerization. no need ...
A Python-based MCP server that lets Claude run boto3 code to query and manage AWS resources. Execute powerful AWS operations directly through Claude with proper sandboxing and containerization. No need for complex setups - just pass your AWS credenti
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Python-based MCP server that lets Claude run boto3 code to
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aws-resources-pythonConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS Resources
mcp-server-aws-resources-python is a Python-based MCP server that lets AI assistants like Claude query and manage any AWS resource by generating and executing boto3 code snippets in a sandboxed environment. It runs via Docker (no git clone needed) and accepts AWS credentials as environment variables. The server exposes a single powerful tool, aws_resources_query_or_modify, that executes validated Python boto3 snippets and returns JSON-serialized results — covering everything from listing S3 buckets to checking CodePipeline deployments.
Prerequisites
- Docker installed and running (the server runs as a Docker container)
- AWS credentials: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, and optionally AWS_SESSION_TOKEN
- An IAM user or role with permissions for the AWS services you want to query
- An MCP client such as Claude Desktop or Claude Code
- AWS_DEFAULT_REGION set (defaults to us-east-1 if not provided)
Pull the Docker image
Pull the pre-built multi-platform Docker image from Docker Hub. Supports linux/amd64, linux/arm64, and linux/arm/v7.
docker pull buryhuang/mcp-server-aws-resources:latestVerify your AWS credentials
Ensure your IAM user has the necessary permissions for the AWS services you want to query. The server does not restrict to read-only operations — your IAM permissions are the only guardrail.
aws sts get-caller-identityAdd to Claude Desktop using Docker with explicit credentials
Edit your claude_desktop_config.json to run the MCP server container with AWS credentials passed as environment variables.
{
"mcpServers": {
"aws-resources": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "AWS_ACCESS_KEY_ID=your_access_key_id_here",
"-e", "AWS_SECRET_ACCESS_KEY=your_secret_access_key_here",
"-e", "AWS_DEFAULT_REGION=us-east-1",
"buryhuang/mcp-server-aws-resources:latest"
]
}
}
}Alternatively, use AWS profile with mounted credentials
If you prefer using a named AWS profile from your local credentials file, mount your ~/.aws directory and set AWS_PROFILE.
{
"mcpServers": {
"aws-resources": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "AWS_PROFILE=default",
"-v", "~/.aws:/root/.aws",
"buryhuang/mcp-server-aws-resources:latest"
]
}
}
}Query AWS resources through Claude
Once configured, ask Claude to query or manage your AWS resources. The server validates boto3 code with AST analysis and restricts allowed imports before executing. Every snippet must set a 'result' variable that is returned as JSON.
AWS Resources Examples
Client configuration
Claude Desktop config running the AWS Resources server via Docker with explicit credentials.
{
"mcpServers": {
"aws-resources": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "AWS_ACCESS_KEY_ID=your_access_key_id_here",
"-e", "AWS_SECRET_ACCESS_KEY=your_secret_access_key_here",
"-e", "AWS_DEFAULT_REGION=us-east-1",
"buryhuang/mcp-server-aws-resources:latest"
]
}
}
}Prompts to try
Natural language prompts that trigger boto3 code generation and execution against your AWS account.
- "List all S3 buckets in my account and show their creation dates."
- "Show me the status of all EC2 instances in us-east-1."
- "Get the latest successful CodePipeline execution for my pipeline named 'my-deploy-pipeline'."
- "List all Lambda functions and their runtimes."
- "Show me all DynamoDB tables and their item counts."Troubleshooting AWS Resources
Docker container exits immediately or gives 'permission denied' error
Ensure Docker is running and you have permissions to run containers. On Linux, add your user to the docker group: sudo usermod -aG docker $USER and log out/in. Check credentials are correct with: aws sts get-caller-identity
boto3 code execution fails with 'import not allowed' error
The server restricts imports to: boto3, operator, json, datetime, pytz, dateutil, re, and time. Any other import will be rejected by the AST validator. Restructure your query to use only these allowed modules.
AWS API calls return AccessDenied errors
The server's permissions are determined entirely by your IAM user or role. Attach the necessary IAM policies to your user. For read-only auditing, attach ReadOnlyAccess. For management operations, add the specific service policies needed.
Frequently Asked Questions about AWS Resources
What is AWS Resources?
AWS Resources is a Model Context Protocol (MCP) server that python-based mcp server that lets claude run boto3 code to query and manage aws resources. execute powerful aws operations directly through claude with proper sandboxing and containerization. no need for complex setups - just pass your aws credenti It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS Resources?
Follow the installation instructions on the AWS Resources GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AWS Resources?
AWS Resources works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS Resources free to use?
Yes, AWS Resources is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
AWS Resources Alternatives — Similar Cloud Services Servers
Looking for alternatives to AWS Resources? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AWS Resources in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AWS Resources?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.