# AWS — MCP Server

> Query AWS docs, pricing and infrastructure through an AI agent.

**Source:** https://mcpplaygroundonline.com/mcp-servers/aws  
**Transport:** stdio  
**Requires auth:** Yes

---

## What it does

The awslabs/mcp repository hosts a family of focused MCP servers, each wrapping a different slice of AWS. The Documentation server searches and retrieves AWS docs so an agent stops guessing at service limits and parameter names. The Cloud Control API server creates, reads, updates, deletes and lists AWS resources from natural language, covering hundreds of resource types through one uniform interface. Others cover pricing, CDK, Terraform, diagrams and per-service APIs. They run locally over stdio and authenticate with your existing AWS credential chain, which means an agent inherits exactly the IAM permissions of the profile you point it at.

## Tools exposed

- aws-documentation-mcp-server — search AWS docs and get content recommendations
- aws-api-mcp-server — general AWS API access from natural language
- ccapi-mcp-server — create, read, update, delete and list resources via Cloud Control API
- aws-pricing-mcp-server — query service pricing and estimate costs
- cdk-mcp-server — CDK construct guidance and best practices
- aws-network-mcp-server — VPC and networking operations

## Example queries you can run

- "What are the current limits on Lambda concurrent executions, and how do I raise them?"
- "List every S3 bucket in us-east-1 and flag any without default encryption."
- "Estimate the monthly cost of an RDS db.r6g.large running 24/7 in eu-west-1."
- "Which CDK construct should I use for an ALB in front of a Fargate service?"

## Details

- **Recommended model:** anthropic/claude-sonnet-4.5 — AWS work is multi-step and unforgiving about parameter names. Sonnet 4.5 chains documentation lookups into concrete actions without inventing service limits.
- **Transport:** stdio
- **Authentication:** Required — Uses your standard AWS credential chain — profile, environment variables or SSO. The agent inherits that profile's IAM permissions exactly.
- **Official source:** [awslabs/mcp — official repository](https://github.com/awslabs/mcp)

## Frequently asked questions

### Is there a single AWS MCP server?

No, and that trips people up. AWS Labs ships a suite of focused servers in the awslabs/mcp repository — documentation, pricing, CDK, Cloud Control API, networking and more. You install the ones matching your work rather than connecting to one endpoint.

### Which AWS MCP server should I start with?

The documentation server. It is read-only, so there is no blast radius, and it fixes the most common failure — an agent inventing service limits or parameter names. Add the Cloud Control API server once you actually want the agent changing resources.

### How does authentication work for AWS MCP servers?

They use the standard AWS credential chain: a named profile, environment variables or SSO. That means the agent has exactly the IAM permissions of whichever profile you point it at, so scoping that profile tightly is your main safety control.

### Is it safe to let an AI agent manage AWS resources?

Only with a scoped IAM role. Start read-only, and if you enable the Cloud Control API server, use a profile limited to a non-production account. The agent will do exactly what its credentials permit, which is the whole risk.

### Are the AWS MCP servers hosted or local?

Local. They run over stdio and are distributed through PyPI and container images rather than as a hosted endpoint, which is why they use your local credential chain instead of asking for a key.

---

_Test this server across 40+ models on MCP Playground: https://mcpplaygroundonline.com/mcp-servers/aws — free, no install._