io.github.musaddiq-dev/aws-cli-mcp-server
A Python MCP server that lets MCP-compatible clients inspect and operate AWS through the AWS CLI, with command execution, suggestions, region lookup, and caller identity checks.
README
<!-- mcp-name: io.github.musaddiq-dev/aws-cli-mcp-server -->
AWS MCP Server
A Python Model Context Protocol (MCP) server that lets MCP-compatible clients inspect and operate AWS through the AWS CLI. It supports command execution with validation, command suggestions, AWS region lookup, and caller identity checks.
Features
- Execute AWS CLI commands without shell expansion, preserving quoted arguments with shell-style parsing
- Suggest common AWS CLI commands from natural language requests
- Return available AWS regions
- Return the current caller identity
- Support stdio transport for local MCP clients
- Validate configuration and write logs to stderr plus a local log file
Safety Model
This server can execute AWS CLI commands using the credentials available to the process. It blocks shell operators by using subprocess.run(..., shell=False) and flags destructive-looking commands, but it cannot replace IAM least privilege or human review. Use scoped AWS profiles or roles, prefer non-production accounts for testing, and keep destructive commands on manual approval in your MCP client.
Requirements
- Python 3.12+
- AWS CLI v2 installed and available on
PATH - AWS CLI authentication configured and configuration through an AWS profile, IAM Identity Center/SSO, environment variables, an IAM role, or another AWS-supported credential provider
- MCP-compatible client such as Claude Desktop, Cursor, VS Code, or another MCP host
Installation
When published to PyPI, install or run the server like a standard Python MCP package:
uvx mdev-aws-mcp-server
For local development from source:
git clone https://github.com/musaddiq-dev/aws-cli-mcp-server.git
cd aws-cli-mcp-server
python -m venv .venv
source .venv/bin/activate
pip install -e .
Configuration
Before running this server, install the AWS CLI using the official AWS CLI install guide, then configure credentials using the official AWS CLI sign-in guide and AWS CLI configuration guide. AWS recommends short-term credentials where possible; avoid long-term IAM user keys unless your use case requires them.
Copy the example environment file and adjust values as needed.
cp .env.example .env
| Variable | Description | Default |
|---|---|---|
AWS_REGION |
Default AWS region | us-east-1 |
AWS_PROFILE |
AWS credentials profile | default |
AWS_MCP_WORKING_DIR |
Working directory for file operations | /tmp/aws-mcp-work |
AWS_MCP_REQUIRE_CONFIRMATION |
Emit warnings for destructive-looking operations | true |
AWS_MCP_LOG_LEVEL |
Application log level | INFO |
Running
mdev-aws-mcp-server
From a local checkout before PyPI publication, run:
python -m aws_mcp_server.server
MCP Client Configuration
For published installs, prefer uvx. MCP servers using stdio must write protocol messages only to stdout; this server writes logs to stderr and a local file under ~/.aws-mcp-server/logs.
Claude Desktop / Cursor / Windsurf / Cline
Most MCP clients accept this mcpServers JSON shape:
{
"mcpServers": {
"aws": {
"command": "uvx",
"args": ["mdev-aws-mcp-server"],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
For local development from this repository, use the installed console script path instead:
{
"mcpServers": {
"aws": {
"command": "/absolute/path/to/aws-cli-mcp-server/.venv/bin/mdev-aws-mcp-server",
"args": [],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
Claude Code CLI
claude mcp add aws --env AWS_PROFILE=default --env AWS_REGION=us-east-1 -- uvx mdev-aws-mcp-server
VS Code MCP
VS Code uses the same command/args/env model in its MCP configuration:
{
"servers": {
"aws": {
"type": "stdio",
"command": "uvx",
"args": ["mdev-aws-mcp-server"],
"env": {
"AWS_PROFILE": "default",
"AWS_REGION": "us-east-1"
}
}
}
}
Tools
| Tool | Purpose | Safety |
|---|---|---|
call_aws |
Execute an AWS CLI command | Can modify AWS resources |
suggest_aws_commands |
Suggest common AWS CLI commands | Read-only |
get_aws_regions |
List AWS regions | Read-only |
get_caller_identity |
Return current AWS identity | Read-only |
Development
pip install -e .
pip install -e '.[dev]'
pytest
ruff check .
ruff format .
pyright
Smoke Check
python -m py_compile src/aws_mcp_server/server.py src/aws_mcp_server/config.py src/aws_mcp_server/aws/executor.py
python -m pytest
Manual AWS check, if credentials are configured:
aws sts get-caller-identity
Distribution
This server is published through the standard Python MCP distribution path:
- PyPI package:
mdev-aws-mcp-server - MCP Registry name:
io.github.musaddiq-dev/aws-cli-mcp-server - Runtime hint:
uvx - Transport:
stdio
The mcp-name marker at the top of this README is required for MCP Registry ownership verification. Users should prefer uvx mdev-aws-mcp-server in local MCP client configurations.
Security Notes
- Do not commit
.env, AWS credentials, profiles, access keys, or account-specific outputs. - Use least-privilege IAM permissions for the profile or role running this server.
- Keep
call_awson explicit manual approval in your MCP client. - Do not expose this server over a network without adding authentication, TLS, and network controls.
- Review generated command suggestions before executing them.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。