aws-mcp-server
A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.
AWS MCP Server
Give Claude access to all 200+ AWS services through the AWS CLI.
Demo
What It Does
This MCP server lets Claude run AWS CLI commands on your behalf. Instead of wrapping each AWS API individually, it wraps the CLI itself—giving Claude complete AWS access through just two tools:
| Tool | Purpose |
|---|---|
aws_cli_help |
Get documentation for any AWS command |
aws_cli_pipeline |
Execute AWS CLI commands with optional pipes (jq, grep, etc.) |
Claude learns commands on-demand using --help, then executes them. Your IAM policy controls what it can actually do.
flowchart LR
Claude[Claude] -->|MCP| Server[AWS MCP Server]
Server --> CLI[AWS CLI]
CLI --> AWS[AWS Cloud]
IAM[Your IAM Policy] -.->|controls| AWS
What's New
- Streamable HTTP transport — New
streamable-httptransport for web-based MCP clients, replacing the deprecatedssetransport (#33) - Input validation error handling — Validation errors now return proper MCP tool errors (
isError: true) instead of regular results (#34) - Server description — Server advertises its purpose to MCP clients via the
instructionsfield (#35) - Server icons — Server provides icon metadata for MCP client display (#36)
- Graceful shutdown — Server disconnects cleanly when the MCP client disconnects (#16)
Quick Start
Prerequisites
- AWS CLI installed
- AWS credentials configured (see AWS Credentials)
- uv installed (for
uvx)
Claude Code
Add to your MCP settings (Cmd+Shift+P → "Claude: Open MCP Config"):
{
"mcpServers": {
"aws": {
"command": "uvx",
"args": ["aws-mcp"]
}
}
}
Claude Desktop
Add to your Claude Desktop config file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\\Claude\\claude_desktop_config.json
{
"mcpServers": {
"aws": {
"command": "uvx",
"args": ["aws-mcp"]
}
}
}
Docker (More Secure)
Docker provides stronger isolation by running commands in a container:
{
"mcpServers": {
"aws": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-v",
"~/.aws:/home/appuser/.aws:ro",
"ghcr.io/alexei-led/aws-mcp-server:latest"
]
}
}
}
Note: Replace
~/.awswith the full path on Windows (e.g.,C:\\Users\\YOU\\.aws).
Docker with Streamable HTTP Transport
For web-based MCP clients, use the streamable-http transport:
docker run --rm -p 8000:8000 \\
-e AWS_MCP_TRANSPORT=streamable-http \\
-v ~/.aws:/home/appuser/.aws:ro \\
ghcr.io/alexei-led/aws-mcp-server:latest
The server will be available at http://localhost:8000/mcp.
Note: The
ssetransport is deprecated. Usestreamable-httpinstead.
AWS Credentials
The server uses the standard AWS credential chain. Your credentials are discovered automatically from:
- Environment variables:
AWS_ACCESS_KEY_ID,AWS_SECRET_ACCESS_KEY - Credentials file:
~/.aws/credentials - Config file:
~/.aws/config(for profiles and region) - IAM role: When running on EC2, ECS, or Lambda
To use a specific profile:
{
"mcpServers": {
"aws": {
"command": "uvx",
"args": ["aws-mcp"],
"env": {
"AWS_PROFILE": "my-profile"
}
}
}
}
Configuration
AWS Settings
| Environment Variable | Description | Default |
|---|---|---|
AWS_PROFILE |
AWS profile to use | default |
AWS_REGION |
AWS region (also accepts AWS_DEFAULT_REGION) |
us-east-1 |
AWS_CONFIG_FILE |
Custom path to AWS config file | ~/.aws/config |
AWS_SHARED_CREDENTIALS_FILE |
Custom path to credentials file | ~/.aws/credentials |
Server Settings
| Environment Variable | Description | Default |
|---|---|---|
AWS_MCP_TIMEOUT |
Command execution timeout in seconds | 300 |
AWS_MCP_MAX_OUTPUT |
Maximum output size in characters | 100000 |
AWS_MCP_TRANSPORT |
Transport protocol (stdio, sse, or streamable-http) |
stdio |
AWS_MCP_SANDBOX |
Sandbox mode (auto, disabled, required) |
auto |
AWS_MCP_SANDBOX_CREDENTIALS |
Credential passing (env, aws_config, both) |
both |
Security
Your IAM policy is your security boundary. This server executes whatever AWS commands Claude requests—IAM controls what actually succeeds.
Best practices:
- Use a least-privilege IAM role (only permissions Claude needs)
- Never use root credentials
- Consider Docker for additional host isolation
For detailed security architecture, see Security Documentation.
Documentation
- Usage Guide — Tools, resources, and prompt templates
- Security Architecture — IAM + Sandbox + Docker model
- Development Guide — Contributing and testing
License
MIT License — see LICENSE for details.
Recommend MCP Servers 💡
@rashidazarang/airtable-mcp
Airtable integration for AI-powered applications via Anthropic's Model Context Protocol (MCP)
cloudflare-remote-mcp-server
A remote MCP server running on Cloudflare Workers using SSE transport, enabling integration with AI models like Claude
telnyx-mcp-server
Official Telnyx MCP Server enabling interaction with telephony, messaging, and AI assistant APIs for MCP clients.
openapi-mcp-server
Allow AI to wade through complex OpenAPIs using Simple Language
anandkumarpatel/remote-mcp-server
A remote Model Context Protocol (MCP) server designed to run on Cloudflare Workers, featuring OAuth login and demonstrating integration with MCP Inspector and Claude Desktop.
opslevel-mcp
Model Context Protocol (MCP) server for OpsLevel