HEALTH AUDIT TOOL - Detect anomalies and unhealthy services in a group. Use this tool when users ask: - "Is the Payment application healthy?" - "Are there any unhealthy services in Topology?" - "Which services have high fault rates in the checkout group?" - "Check the health of the API group" - ...
Part of the CloudWatch Application Signals MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call audit_group_health 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.
Even though audit_group_health 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:
audit_group_health:
rules:
- action: allowSee the full CloudWatch Application Signals MCP Server policy for all 22 tools.
Agents calling read-class tools like audit_group_health 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.
HEALTH AUDIT TOOL - Detect anomalies and unhealthy services in a group. Use this tool when users ask: - "Is the Payment application healthy?" - "Are there any unhealthy services in Topology?" - "Which services have high fault rates in the checkout group?" - "Check the health of the API group" - "Any anomalies in the Payment services?" **WHAT THIS TOOL DOES:** 1. **SLI-First**: First checks Service Level Indicators (SLOs) for each service. If SLOs are configured, uses SLO breach status for health assessment. 2. **Metrics Fallback**: For services without SLOs, falls back to raw metrics (fault rate, error rate, latency) with configurable thresholds. **HEALTH ASSESSMENT:** - SLI Mode: CRITICAL if any SLO is breached, OK otherwise - Metrics Mode: Based on fault/error rate thresholds **OUTPUT INCLUDES:** - Data source indicator (SLI vs Metrics) per service - Health summary (critical/warning/healthy counts) - Breached SLO names (if using SLI) - Detailed anomaly list with severity - Recommendations for investigation **EXAMPLES:** ``` audit_group_health(group_name='Payments') audit_group_health(group_name='Checkout', fault_threshold_critical=15.0) ```. It is categorised as a Read tool in the CloudWatch Application Signals 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 audit_group_health. 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.
audit_group_health 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 audit_group_health 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 audit_group_health. 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.
audit_group_health 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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.