AWS CLI Bridge
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 infrastruc
What is AWS CLI Bridge?
AWS CLI Bridge is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 ...
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 infrastruc
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A lightweight service that enables AI assistants to execute
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx aws-model-context-protocol-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS CLI Bridge
The AWS MCP Server bridges AI assistants like Claude and Cursor with the AWS CLI, letting them discover and execute any AWS command through two focused tools: one for fetching CLI help documentation and one for running commands with optional Unix pipeline processing. Commands run inside a safe sandboxed environment, and all AWS credential management is handled through the standard AWS config/credentials files or environment variables. This server is ideal for DevOps engineers and cloud architects who want to manage AWS infrastructure — querying resources, deploying stacks, inspecting logs — through natural language without switching context to a terminal.
Prerequisites
- Docker installed (required for the default sandboxed execution mode)
- AWS CLI configured with valid credentials (via ~/.aws/credentials or environment variables)
- Python 3.11+ and uv package manager, or Docker for the containerized deployment
- An IAM user or role with permissions matching the operations you intend to perform
- An MCP-compatible client such as Claude Desktop or Claude Code
Install via uvx (stdio transport)
The simplest deployment uses uvx to run the server directly. AWS credentials are picked up from your standard ~/.aws directory.
uvx aws-mcpAlternative: run with Docker (HTTP transport)
For remote or team deployments, run as a container with Streamable HTTP transport. Mount your AWS credentials as read-only.
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:latestConfigure AWS credentials
Set the AWS_PROFILE and AWS_REGION environment variables in the MCP server config if you want to use a non-default profile or region.
Add the server to your MCP client
Add the server block to your claude_desktop_config.json or Claude Code settings. The uvx command requires no additional installation steps.
Test with a safe read-only command
Ask the assistant to list your S3 buckets or describe EC2 instances. The server will first learn the command syntax via --help, then execute it.
AWS CLI Bridge Examples
Client configuration
Add to your claude_desktop_config.json. Optionally set AWS_PROFILE and AWS_REGION to target a specific account and region.
{
"mcpServers": {
"aws": {
"command": "uvx",
"args": ["aws-mcp"],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1",
"AWS_MCP_TIMEOUT": "300",
"AWS_MCP_SANDBOX": "auto"
}
}
}
}Prompts to try
Example prompts covering common AWS operations from resource discovery to cost analysis.
- "List all my S3 buckets and their creation dates"
- "Describe all running EC2 instances in us-east-1 and show their instance types"
- "Show me the last 50 CloudWatch log events from the /aws/lambda/my-function log group"
- "List all CloudFormation stacks and their statuses"
- "What IAM policies are attached to the role named MyLambdaRole?"
- "Get the current AWS bill estimate for this month"Troubleshooting AWS CLI Bridge
Commands fail with 'Unable to locate credentials'
Ensure ~/.aws/credentials exists and contains a [default] profile (or set AWS_PROFILE to a valid profile name). When using Docker, confirm the volume mount -v ~/.aws:/home/appuser/.aws:ro is present in the run command.
Sandbox mode blocks command execution
Set AWS_MCP_SANDBOX=disabled in the env block if you want commands to run without the sandbox. Note: only do this in trusted environments since it removes the execution isolation layer.
Output is truncated for large AWS responses
Increase AWS_MCP_MAX_OUTPUT beyond the default of 100000 characters, or use the pipeline feature (jq/grep) to filter results before they reach the output limit.
Frequently Asked Questions about AWS CLI Bridge
What is AWS CLI Bridge?
AWS CLI Bridge is a Model Context Protocol (MCP) server that 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 infrastruc It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS CLI Bridge?
Follow the installation instructions on the AWS CLI Bridge GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with AWS CLI Bridge?
AWS CLI Bridge works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS CLI Bridge free to use?
Yes, AWS CLI Bridge is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
AWS CLI Bridge Alternatives — Similar Cloud Services Servers
Looking for alternatives to AWS CLI Bridge? 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 CLI Bridge 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 CLI Bridge?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.