Queries AWS CloudWatch Logs for systemic infrastructure errors. Searches the last 15 minutes by default.
AI agents call checkCloudTrailLogs to retrieve information from Bedrock Agent Core Operations Hub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and inspects log data from AWS CloudWatch to detect infrastructure errors. Querying logs is a non-destructive read operation that returns information about system state without altering infrastructure, data, or configurations. The blast radius of misuse is limited to information disclosure of logs that an operations team would typically have access to review anyway.
From the tool's definition Tool description states it 'Queries AWS CloudWatch Logs' and 'Searches the last 15 minutes by default.' The verb 'Queries' and the read-only nature of CloudWatch Logs inspection indicate data retrieval with no modifications or side effects.
Attacks that exploit this kind of access
Queries AWS CloudWatch Logs for systemic infrastructure errors. Searches the last 15 minutes by default. It is categorised as a Read tool in the Bedrock Agent Core Operations Hub MCP Server, which means it retrieves data without modifying state.
Register the Bedrock Agent Core Operations Hub MCP server in PolicyLayer and add a rule for checkCloudTrailLogs: 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 Bedrock Agent Core Operations Hub. Nothing to install.
checkCloudTrailLogs 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 checkCloudTrailLogs 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 checkCloudTrailLogs. 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.
checkCloudTrailLogs is provided by the Bedrock Agent Core Operations Hub MCP server (sujithpvarghese/bedrock-agent-core-operations-hub-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 →