sam_deploy
AI agents invoke sam_deploy to trigger actions in Amazon MQ MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Deployment tools execute external operations (CloudFormation stack updates) whose effects depend on the SAM template provided as argument. This is Execute rather than Write because it triggers infrastructure provisioning and orchestration beyond simple data modification. Severity is high due to potential blast radius from misconfigured infrastructure, resource creation costs, and security exposure.
From the tool's definition Tool name 'sam_deploy' indicates deployment of AWS Serverless Application Model (SAM) applications. Despite empty description, SAM deployment triggers creation and modification of cloud infrastructure, executing infrastructure-as-code templates that provision…
Attacks that exploit this kind of access
sam_deploy. It is categorised as a Execute tool in the Amazon MQ MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Amazon MQ MCP Server MCP server in PolicyLayer and add a rule for sam_deploy: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Amazon MQ MCP Server. Nothing to install.
sam_deploy is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sam_deploy rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for sam_deploy. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
sam_deploy is provided by the Amazon MQ MCP Server MCP server (awslabs.amazon-mq-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.