query_rum_events

// WHEN AI AGENTS USE THIS TOOL

AI agents call query_rum_events to retrieve information from CloudWatch Application Signals 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.

// WHY ENFORCE A POLICY ON QUERY_RUM_EVENTS

Even though query_rum_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.

// RECOMMENDED POLICY

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

cloudwatch-application-signals-mcp-server.yaml

tools:
  query_rum_events:
    rules:
      - action: allow

See the full CloudWatch Application Signals MCP Server policy for all 22 tools.

// DETAILS

Tool Name query_rum_events

Category Read

MCP Server CloudWatch Application Signals MCP Server MCP Server

Risk Level Low

// MORE CLOUDWATCH APPLICATION SIGNALS MCP SERVER TOOLS

Read analyze_canary_failures Read audit_group_health Read audit_service_operations Read audit_services Read audit_slos Read get_enablement_guide Read get_group_changes Read get_group_dependencies

View all 22 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like query_rum_events have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER READ TOOLS ACROSS MCP SERVERS

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

Firecrawl Web Scraping Server firecrawl_check_crawl_status Firecrawl Web Scraping Server firecrawl_crawl Firecrawl Web Scraping Server firecrawl_deep_research Firecrawl Web Scraping Server firecrawl_extract Firecrawl Web Scraping Server firecrawl_map Firecrawl Web Scraping Server firecrawl_scrape

// RELATED READING

// FAQ

What does the query_rum_events tool do? +

CloudWatch RUM – monitor real user experience across web and mobile apps. Use the ``action`` parameter to select an operation. All other parameters are optional and depend on the chosen action. **Actions & required parameters** (JSON shape — keys are action names, values are required parameter names): ```json { "check_data_access": ["app_monitor_name"], "list_monitors": [], "get_monitor": ["app_monitor_name"], "list_tags": ["resource_arn"], "get_policy": ["app_monitor_name"], "query": ["app_monitor_name", "query_string", "start_time", "end_time"], "health": ["app_monitor_name", "start_time", "end_time"], "errors": ["app_monitor_name", "start_time", "end_time"], "performance": ["app_monitor_name", "start_time", "end_time"], "sessions": ["app_monitor_name", "start_time", "end_time"], "session_detail": ["app_monitor_name", "session_id", "start_time", "end_time"], "page_views": ["app_monitor_name", "start_time", "end_time"], "timeseries": ["app_monitor_name", "start_time", "end_time"], "locations": ["app_monitor_name", "start_time", "end_time"], "http_requests": ["app_monitor_name", "start_time", "end_time"], "resources": ["app_monitor_name", "start_time", "end_time"], "page_flows": ["app_monitor_name", "start_time", "end_time"], "crashes": ["app_monitor_name", "start_time", "end_time"], "app_launches": ["app_monitor_name", "start_time", "end_time"], "analyze": ["app_monitor_name", "start_time", "end_time"], "correlate": ["app_monitor_name", "page_url", "start_time", "end_time"], "metrics": ["app_monitor_name", "metric_names", "start_time", "end_time"], "slo_health": ["app_monitor_name", "start_time", "end_time"] } ``` Optional params: ``compare_previous`` (health), ``page_url``/``group_by`` (errors, performance, locations, http_requests, resources, timeseries), ``metric``/``bucket`` (timeseries), ``platform`` (crashes, app_launches — 'ios'/'android'/'all'), ``max_results`` (list_monitors, query; capped at 200 for query), ``max_traces`` (correlate), ``statistic``/``period`` (metrics), ``limit`` (session_detail — default 100). All responses are read-only. Logs Insights is the query engine; the server does not write any data.. It is categorised as a Read tool in the CloudWatch Application Signals MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_rum_events? +

Add a rule in your Intercept YAML policy under the tools section for query_rum_events. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the CloudWatch Application Signals MCP Server MCP server.

What risk level is query_rum_events? +

query_rum_events is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit query_rum_events? +

Yes. Add a rate_limit block to the query_rum_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.

How do I block query_rum_events completely? +

Set action: deny in the Intercept policy for query_rum_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.

What MCP server provides query_rum_events? +

query_rum_events is provided by the CloudWatch Application Signals MCP Server MCP server (awslabs.cloudwatch-applicationsignals-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.