Cloud infrastructure

AWS logo

AWS MCP server

Give AI agents governed access to the AWS MCP server through one audited gateway. Scoped permissions, full observability, and tamper-evident logs on every tool call.

What is the AWS MCP server?

The AWS MCP server is an open Model Context Protocol (MCP) server that connects AI agents to AWS cloud resources across services like EC2, S3, Lambda, and CloudWatch. Through it an agent can list resources, read metrics, and inspect configuration without bespoke integration code, while the Averta MCP Gateway keeps every action scoped and audited.

aws-list-ec2-instances

List EC2 instances and their states.

aws-describe-instance

Read configuration for an instance.

aws-list-s3-buckets

List S3 buckets and their regions.

aws-get-cloudwatch-metrics

Read CloudWatch metrics for a resource.

aws-list-lambda-functions

List Lambda functions and runtimes.

aws-describe-rds

Read RDS database configuration.

aws-get-cost

Read cost and usage with Cost Explorer.

aws-list-iam-roles

List IAM roles and policies.

aws-get-logs

Read CloudWatch log streams.

aws-list-ecs-services

List ECS services and task counts.

Why the Averta MCP Gateway

Centralized governance

Unified authentication, audit logging, and rate control for every AWS MCP connection.

Observability and control

Real-time visibility into usage, anomalies, and SLA compliance across every request.

One-click deployment

Enable the AWS MCP server for your AI teams through one governed gateway, with no manual setup.

Enterprise hardening

High availability, security, and compliance alignment turn MCP from a developer utility into production-grade infrastructure.

OAuth and SSO enforcement

Enterprise authentication and SSO applied automatically to every AWS endpoint.

Shared and per-user auth

Configure service accounts or per-user access, with secrets protected and centralized revocation.

One managed endpoint

Connect agents to AWS through a single governed endpoint instead of locally run servers, improving your security posture.

Granular tool access control

Allow only the tools each role needs. Enable read-only access and block write tools like create and delete.

Works with every major AI platform

ChatGPT logoChatGPT
Gemini logoGemini
Mistral logoMistral
Claude Code logoClaude Code
Cursor logoCursor
Windsurf logoWindsurf
Cognition logoCognition
OpenCode logoOpenCode
Continue logoContinue
Manus logoManus
Hermes logoHermes
Lindy logoLindy
OpenClaw logoOpenClaw
Your own logoYour own

Built for enterprise teams.

Cloud, private VPC, embedded SDK, or gateway integration. Run Averta where your data, policies, and auditors need it.

AWS
Google Cloud
Azure
Oracle
Book a demo

Cloud (SaaS)

Fully managed by Averta. Fastest path to production, no infrastructure to run.

Private / VPC

Deploy in your own environment, so data never leaves your boundary.

Embedded SDK & Proxy

Drop Averta into your stack at the SDK or proxy layer, wherever your agents run.

Gateway Integration

Route agent traffic through the gateway, so policy and audit apply at the edge.

AWS MCP use cases

Where teams put the AWS MCP server to work, governed end to end through the Averta MCP Gateway.

Agents list resources and their states across services, read-only.

Book a demo
AWS MCP · Resource inventory

List running EC2 instances in us-east-1.

You

Listed running instances in us-east-1.

  • Listing EC2 instances
  • Filtering by region and state

All actions logged and governed

Powering safe AI execution at leading teams.

Cyfrin secures its production AI agents with Averta.

Book a demo
Averta gave our agents enforceable boundaries for the dev environment, so instructions like ‘don’t read .env files’ became policy instead of polite suggestions.
Mikhail Karan

Mikhail Karan

Head of Engineering

Explore other MCP servers

AWS MCP server, answered

Security and setup questions teams ask before connecting the AWS MCP server to AI agents.

Yes. The Averta MCP Gateway sits between your AI agents and any MCP server, giving each agent scoped, per-agent permissions, applying allow, escalate, or block policies on every tool call, and recording a tamper-evident audit of every action. The “Why the Averta MCP Gateway” section on this page covers what it enforces.

It is as safe as the controls around it. The server can reach cloud resources through one set of credentials, so scoping to read-only and specific services is the real risk. The Averta MCP Gateway limits and records every call.

Apply tool-level policy through the Averta MCP Gateway so describe and read operations run automatically while any mutating action escalates for approval. Every call is logged.

Route agents through Averta's MCP Gateway for scoped per-agent permissions, tool-level policy, and tamper-evident audit across every AWS action.

Yes. AWS Labs publishes a suite of official MCP servers, including ones for AWS documentation, knowledge, S3, Lambda, and serverless. Whichever you run, routing it through the Averta MCP Gateway gives each agent scoped, read-first access with a tamper-evident audit trail.

See Averta OS in action

Book a demo and see how Averta OS secures your AI agents from input to execution.

Book a demo