A Python MCP server that lets compatible clients run AWS CLI commands through the AWS CLI, with validation, command suggestions, region lookup, and caller identity checks. It uses stdio transport and logs locally while executing commands with the credentials configured for the process.
From the registry: Python MCP server for AWS CLI inspection and operations
Please install the `aws-cli-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Python 3.12+** — Python 3.12 or newer is required to run the server via uvx.
- **Install AWS CLI v2** — Install the AWS CLI v2 and ensure the aws command is available on PATH. (https://docs.aws.amazon.com/cli/latest/userguide/getting-started-install.html)
- **Configure AWS authentication** — Configure AWS credentials and configuration using an AWS profile, IAM Identity Center/SSO, environment variables, an IAM role, or another AWS-supported credential provider. (https://docs.aws.amazon.com/cli/latest/userguide/cli-configure-sign-in.html)
- **Install uvx** — Install uvx so the published PyPI package can be run with the preferred portable command.
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["mdev-aws-mcp-server"]
- optional environment variables:
- `AWS_REGION`: Default AWS region used by the server. (example: `<your-aws-region>`)
- `AWS_PROFILE`: AWS credentials profile to use for AWS CLI commands. (example: `<your-aws-profile>`)
- `AWS_MCP_WORKING_DIR`: Working directory for file operations. (example: `<your-working-directory>`)
- `AWS_MCP_REQUIRE_CONFIRMATION`: Whether to emit warnings for destructive-looking operations. (example: `<true-or-false>`)
- `AWS_MCP_LOG_LEVEL`: Application log level. (example: `<your-log-level>`)
Note: Prefer the published stdio install path: uvx mdev-aws-mcp-server. The README examples commonly set AWS_PROFILE and AWS_REGION, but AWS authentication may also come from other AWS-supported credential providers, so these env vars are optional in client config. The server writes protocol messages to stdout and logs to stderr and a local file under ~/.aws-mcp-server/logs.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AWS_REGIONDefault AWS regionAWS_PROFILEAWS credentials profileAWS_MCP_WORKING_DIRWorking directory for file operationsAWS_MCP_REQUIRE_CONFIRMATIONEmit warnings for destructive-looking operationsAWS_MCP_LOG_LEVELApplication log levelReal-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.
Gives AI development tools Firebase-specific capabilities and expertise.
All Azure MCP tools to create a seamless connection between AI agents and Azure services.
MCP tools for interacting with Microsoft Fabric