List CloudWatch log groups, with optional name prefix and full pagination (no 50 cap).
AI agents call get_log_groups 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 metadata about log groups without creating, modifying, deleting, or executing any operations. It has no side effects and poses minimal risk even if misused by an AI agent, as it only exposes the names of existing log group resources. The read-only nature and informational purpose justify 'low' severity.
From the tool's definition Tool 'get_log_groups' lists CloudWatch log groups with optional filtering and pagination. The server is described as providing 'read-only access' and enabling 'log analysis'.
Attacks that exploit this kind of access
List CloudWatch log groups, with optional name prefix and full pagination (no 50 cap). 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_log_groups: 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_log_groups 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_log_groups 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_log_groups. 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_log_groups 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 →