Amazon AWS Serverless MCP Server

Amazon Web Services's AWS Serverless MCP server connects AI agents to AWS Lambda, Amazon API Gateway, and AWS SAM to inspect, configure, and monitor serverless applications. It enables agents to check function metrics, trace execution logs, and optimize event-driven architectures.

Start for free

Benefits with Ory + Amazon AWS Serverless MCP Server

Amazon Web Services' AWS Serverless MCP server helps your agents build, deploy, and troubleshoot serverless applications with AWS SAM, AWS Lambda, and related services, including reading metrics and logs. A deployment from an agent can change live functions and APIs. Ory Agent Security lets agents read metrics and logs while deployments stay with the agents you approve, and every tool call is tied to the user behind it.

View documentation

Use Cases

— 01 use case

Agent IAM

Debuggers read logs at Read, scaffolding agents get Write, deploys stay with a release agent at Admin, and Block covers agents outside the serverless team.

Explore Agent IAM

Core Functionality

— 04 capabilities

Read, write, admin, or no access
Ory Agent Security classifies every tool on the AWS Serverless MCP server as read, write, or admin, so you can give each user, team, or agent type only the level it needs: read for monitoring agents, write for agents scaffolding new projects, admin for deployment agents, and no access for agents with no role in your serverless apps.
Enforced before execution
Ory Agent Security checks each tool call against the user, the agent acting for them, and any sub-agent inside the agent harness, so a denied deployment stops before it reaches AWS, with nothing to roll back and no gateway to deploy.
Observe, then enforce
Observe mode shows which agents deploy functions and for whom without blocking anything, so you can apply Ory's pre-built policy for the AWS Serverless MCP server and enforce it on your own schedule.
Complete audit trail
Every allow and deny decision on the AWS Serverless MCP server streams to your SIEM through OpenTelemetry with the user, agent, and action attached, so you can show which agent pushed a change live and which user it acted for.