AWS MCP Servers

Official collection of MCP servers from AWS Labs providing AI agents access to AWS services. Includes servers for AWS documentation lookup, infrastructure-as-code (CloudFormation, CDK, Terraform), container orchestration (EKS, ECS), serverless (SAM CLI, Lambda), cloud resource management (Cloud Control API), and AWS Support. Enables foundation models to read AWS docs, manage infrastructure, and automate cloud operations.

Evaluated Mar 07, 2026 (0d ago) vunknown
Homepage ↗ Repo ↗ Other mcp-server aws cloudformation cdk terraform eks ecs lambda serverless documentation cloud-control infrastructure-as-code
⚙ Agent Friendliness
76
/ 100
Can an agent use this?
🔒 Security
77
/ 100
Is it safe for agents?
⚡ Reliability
75
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
80
Documentation
75
Error Messages
60
Auth Simplicity
80
Rate Limits
72

🔒 Security

TLS Enforcement
90
Auth Strength
75
Scope Granularity
70
Dep. Hygiene
80
Secret Handling
72

Core MCP library/SDK. Foundation for MCP server implementations. Security determined by how it is used. Input validation and output sanitization are developer responsibility.

⚡ Reliability

Uptime/SLA
75
Version Stability
78
Breaking Changes
72
Error Recovery
75
AF Security Reliability

Best When

You work heavily with AWS and want AI coding assistants to have direct access to AWS documentation, infrastructure management, and cloud operations. The official backing from AWS Labs means good maintenance and compatibility.

Avoid When

You don't use AWS, or you need multi-cloud support. Also note that SSE transport was removed -- stdio only, which limits some deployment patterns.

Use Cases

  • AI-assisted AWS infrastructure provisioning and management
  • Querying AWS documentation from within AI coding assistants
  • Infrastructure-as-code generation and validation (CloudFormation, CDK, Terraform)
  • Container orchestration management via AI agents (EKS, ECS)
  • Serverless application development with AI assistance
  • AWS Support case management through AI

Not For

  • Non-AWS cloud providers (Azure, GCP)
  • Production infrastructure automation without human review
  • Real-time monitoring or alerting

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: aws_credentials
OAuth: No Scopes: No

Requires AWS credentials configured via profiles or environment variables. Some servers (like AWS Documentation) may work without credentials for read-only documentation access. One managed remote server exists (AWS MCP Server) that handles auth differently.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

Apache-2.0 licensed. The MCP servers are free; underlying AWS API calls follow standard AWS pricing.

Agent Metadata

Pagination
unknown
Idempotent
Partial
Retry Guidance
Not documented

Known Gotchas

  • SSE transport was removed -- stdio only, which limits remote deployment
  • 12+ individual servers with different capabilities -- agents need to know which to use
  • AWS credentials must be pre-configured -- no interactive auth flow
  • Infrastructure modification servers can make real AWS changes with cost implications
  • Some servers require specific AWS permissions/IAM policies
  • Uses uvx for installation which requires Python environment

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for AWS MCP Servers.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-07.

6228
Packages Evaluated
26150
Need Evaluation
173
Need Re-evaluation
Community Powered