Registry / aws / awslabs-aws-serverless-mcp-server

awslabs-aws-serverless-mcp-server

library0.1.19pypypiunverified

An AWS Labs Model Context Protocol (MCP) server for AWS Serverless, enabling Claude and other AI agents to interact with AWS serverless services. Current version 0.1.19, pre-1.0, actively developed by AWS Labs. Release cadence is irregular.

aws llm-agents devops

pip install awslabs-aws-serverless-mcp-server

github ↗package ↗homepage ↗docs ↗changelog ↗

INSTALL

IMPORT

SIG · AWSLABS-AWS-SERVER

awslabs-aws-serverless-mcp-server

awspythonv0.1.19

Install

10.2s avg

Import

—

Disk

109MB

Pass rate

8/ 10

Env Coverage8 / 10

glibc

3.9–3.13

musl

3.9–3.13

Install & Compatibility

Where this runs

tested against v0.1.19 · pip install

no network on importno background threads

Install × environment matrix

Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux

musl

glibc

py 3.10

✓ —

✓ 12s

py 3.11

✓ —

✓ 11.2s

py 3.12

✓ —

✓ 8.9s

py 3.13

✓ —

✓ 8.6s

py 3.9

✕ build_error

109MB installed

● package 109MB

Code

Verified usage

Verified import paths — ran on the pinned version, not inferred.

create_mcp_server

✓ from awslabs.aws_serverless_mcp_server import create_mcp_server

✗ from awslabs.aws_serverless_mcp_server import create_mcp_server

Creates and runs an MCP server with AWS credentials from environment variables.

import os from awslabs.aws_serverless_mcp_server import create_mcp_server config = MCPServerConfig( aws_region=os.environ.get('AWS_REGION', 'us-east-1'), aws_access_key_id=os.environ.get('AWS_ACCESS_KEY_ID', ''), aws_secret_access_key=os.environ.get('AWS_SECRET_ACCESS_KEY', '') ) server = create_mcp_server(config) server.run()

mcp-server --version

Debug

Known issues

breakingPackage name changed from 'aws-serverless-mcp-server' to 'awslabs-aws-serverless-mcp-server' in version 0.1.0. Update imports and install commands accordingly.

fix

Use 'awslabs-aws-serverless-mcp-server' and 'from awslabs.aws_serverless_mcp_server import ...'

affects: < 0.1.0

deprecatedMCPServerConfig.aws_profile parameter deprecated in 0.1.15, use explicit credentials in config instead.

fix

Pass aws_access_key_id and aws_secret_access_key directly.

affects: >= 0.1.15

gotchaRequires Python >=3.10. Installing on older Python versions will fail silently or with cryptic errors.

fix

Ensure you have Python 3.10+ (python --version) before installing.

affects: all

gotchaAWS credentials are required even for local testing. The server will fail to run without them.

fix

Set AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables, or configure a credentials file.

affects: all

Upgrade

Version history

0.1.19latest on PyPI · released Apr 8, 2026

Audit

Dependencies

mcprequiredCore MCP protocol library required for server functionality

boto3requiredAWS SDK for Python, required for interacting with AWS services

Agent activity

33 hits · last 30 days

node

OpenAI (training)

Resources

githubhttps://github.com/awslabs/mcp ↗

packagehttps://pypi.org/project/awslabs-aws-serverless-mcp-server/ ↗

homepagehttps://awslabs.github.io/mcp/ ↗

docshttps://awslabs.github.io/mcp/servers/aws-serverless-mcp-server/ ↗

changeloghttps://github.com/awslabs/mcp/blob/main/src/aws-serverless-mcp-server/CHANGELOG.md ↗