awslabs.aws-api-mcp-server

What it is and what it does

This package implements a Model Context Protocol (MCP) server that bridges AI assistants with AWS infrastructure. It translates AI requests into AWS CLI commands, allowing tools like Cursor, Kiro, and Cline to create, update, and manage AWS resources without direct AWS console access. The server maintains proper security controls and credential handling through boto3.

The package acts as a runtime adapter between an AI model and AWS services, handling command translation, response parsing, and credential management. It depends on awscli, boto3, botocore, and other standard Python libraries for HTTP communication, logging, and data validation. The server can run in multiple modes: as a subprocess via Python, in Docker containers, or in HTTP mode for remote access. It supports environment-based configuration for AWS regions and authentication methods.

Use it for:

• Enable AI coding assistants to provision EC2 instances, S3 buckets, or other AWS resources directly from chat.
• Allow AI agents to query and modify AWS infrastructure state without manual console navigation.
• Integrate AWS resource management into AI-driven CI/CD or infrastructure-as-code workflows.
• Provide AI models with access to latest AWS APIs and services beyond their training cutoff date.
• Automate AWS CLI command discovery and execution through natural language prompts in AI assistants.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Exposes AWS services to AI assistants through the Model Context Protocol, allowing them to execute AWS CLI commands and interact with AWS resources programmatically.

Yes, with conditions. Install if you use an MCP-compatible AI assistant (Cursor, Kiro, Cline) and need programmatic AWS resource management from AI chat. The package is actively maintained, has low install friction, and carries no license restrictions. However, note that AWS Labs has published an official AWS MCP server that supersedes this one—review the migration guide before committing to this version for new projects. No known security vulnerabilities.

Install

awslabs-aws-api-mcp-server on PyPI

pip install awslabs-aws-api-mcp-server

uv add awslabs-aws-api-mcp-server

poetry add awslabs-aws-api-mcp-server

Installing awslabs.aws-api-mcp-server

Before you install

Low friction installation with a pure-Python wheel. Active maintenance with recent releases (4 days old at query time) and strong repository signals (9598 stars). Requires Python 3.10 or newer and AWS credentials configured; 13 runtime dependencies are standard tools (boto3, awscli, pydantic, loguru, requests).

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions; you must include a copy of the license and state significant changes, but no copyleft obligations apply.

Quickstart

pip install awslabs.aws-api-mcp-server

# Configure in MCP client (e.g., Kiro, Cursor, Cline):
# Add to mcp.json:
# {
#   "mcpServers": {
#     "awslabs.aws-api-mcp-server": {
#       "command": "python",
#       "args": ["-m", "awslabs.aws_api_mcp_server.server"],
#       "env": {"AWS_REGION": "us-east-1"}
#     }
#   }
# }

Requires Python 3.10 or newer and AWS credentials configured (via AWS_API_MCP_PROFILE_NAME environment variable or boto3 default credential chain).

Verify before relying

• Whether the package remains actively maintained after the official AWS MCP server supersedes it (migration guide exists but long-term support unclear).
• Performance characteristics when executing large or complex AWS CLI commands through the MCP bridge.

Package facts

Evidence: awslabs_aws_api_mcp_server-1.5.1-py3-none-any.whl

Tags

More Application Frameworks packages

Further reading