Look up CloudTrail events based on various criteria. This tool searches CloudTrail events using the LookupEvents API, which provides access to the last 90 days of management events. You can filter by time range and search for specific attribute values. Usage: Use this tool to find CloudTrail ev...
Part of the AWS Labs CloudTrail MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call lookup_events to retrieve information from AWS Labs CloudTrail MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though lookup_events only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
lookup_events:
rules:
- action: allowSee the full AWS Labs CloudTrail MCP Server policy for all 5 tools.
Agents calling read-class tools like lookup_events have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Look up CloudTrail events based on various criteria. This tool searches CloudTrail events using the LookupEvents API, which provides access to the last 90 days of management events. You can filter by time range and search for specific attribute values. Usage: Use this tool to find CloudTrail events by various attributes like username, event name, resource name, etc. This is useful for security investigations, troubleshooting, and audit trails. IMPORTANT PAGINATION REQUIREMENTS: - AWS CloudTrail requires pagination tokens to be used with exactly the same parameters as the original request - When using next_token, you must provide the exact same start_time, end_time, attribute_key, and attribute_value - Use the 'query_params' returned in the response for subsequent paginated requests Returns: -------- Dictionary containing: - events: List of CloudTrail events matching the criteria with exact CloudTrail schema - next_token: Token for pagination if more results available - query_params: Parameters used for the query (includes pagination parameters when next_token is present). It is categorised as a Read tool in the AWS Labs CloudTrail MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for lookup_events. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS Labs CloudTrail MCP Server MCP server.
lookup_events 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 lookup_events rule in your Intercept 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 Intercept policy for lookup_events. 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.
lookup_events is provided by the AWS Labs CloudTrail MCP Server MCP server (awslabs.cloudtrail-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.