Aggregate log data for a time range using the specified
AI agents call aggregate_logs to retrieve information from MCP Datadog Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates log data, which is fundamentally a read operation. However, severity is medium rather than low because: (1) logs may contain sensitive information (PII, credentials, business secrets), (2) aggregation at scale could impact system performance, and (3) an AI agent with unrestricted log access could exfiltrate sensitive data.
From the tool's definition Tool name 'aggregate_logs' and description indicating it 'Aggregate log data for a time range' — a query operation that retrieves and processes log data without modification.
Attacks that exploit this kind of access
Aggregate log data for a time range using the specified. It is categorised as a Read tool in the MCP Datadog Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Datadog Server MCP server in PolicyLayer and add a rule for aggregate_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 MCP Datadog Server. Nothing to install.
aggregate_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 aggregate_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 aggregate_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.
aggregate_logs is provided by the MCP Datadog Server MCP server (micaelmalta/mcp-server-datadog). 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 →