get_cloudwatch_logs
AI agents call get_cloudwatch_logs to retrieve information from Amazon MQ MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read operation that queries and retrieves CloudWatch logs—no data is modified, deleted, or executed. However, severity is elevated to medium because logs may contain sensitive information (credentials, API keys, internal system details, application data) that could be exposed if an AI agent over-retrieves or shares logs inappropriately.
From the tool's definition Tool name 'get_cloudwatch_logs' indicates retrieval of log data from CloudWatch. The tool sits on an Amazon MQ management server, where retrieving logs is a standard read operation for monitoring and troubleshooting.
Attacks that exploit this kind of access
get_cloudwatch_logs. It is categorised as a Read tool in the Amazon MQ MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Amazon MQ MCP Server MCP server in PolicyLayer and add a rule for get_cloudwatch_logs: 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.
get_cloudwatch_logs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_cloudwatch_logs 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 get_cloudwatch_logs. 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.
get_cloudwatch_logs 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.