Fetch raw log events in an absolute or relative time window. Optional filterPattern; if omitted, returns ALL events (use this to prove a log line is ABSENT). Returns timestamp + logStreamName (instance) + message, sorted chronologically, paginated. For multi-word phrases use a quoted filterPatter...
AI agents call get_logs to retrieve information from Cloudwatch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries log data without any capability to modify, delete, or execute operations. It is a passive data retrieval mechanism used for debugging and analysis, with no side effects on the CloudWatch system or underlying infrastructure.
From the tool's definition Tool description explicitly states 'Fetch raw log events' and 'returns timestamp + logStreamName + message'. No modification, deletion, or execution capabilities mentioned. Server description emphasizes 'read-only access to AWS CloudWatch Logs'.
Attacks that exploit this kind of access
Fetch raw log events in an absolute or relative time window. Optional filterPattern; if omitted, returns ALL events (use this to prove a log line is ABSENT). Returns timestamp + logStreamName (instance) + message, sorted chronologically, paginated. For multi-word phrases use a quoted filterPattern, e.g. It is categorised as a Read tool in the Cloudwatch MCP Server, which means it retrieves data without modifying state.
Register the Cloudwatch MCP server in PolicyLayer and add a rule for get_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 Cloudwatch. Nothing to install.
get_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_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_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_logs is provided by the Cloudwatch MCP server (shivam-singh-au17/cloudwatch-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →