audit_services

// WHEN AI AGENTS USE THIS TOOL

AI agents call audit_services 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 AUDIT_SERVICES

Even though audit_services 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:
  audit_services:
    rules:
      - action: allow

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

// DETAILS

Tool Name audit_services

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_slos Read get_enablement_guide Read get_group_changes Read get_group_dependencies Read get_service_detail

View all 22 tools →

// WHAT CAN GO WRONG

Agents calling read-class tools like audit_services 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 audit_services tool do? +

PRIMARY SERVICE AUDIT TOOL - The #1 tool for comprehensive AWS service health auditing and monitoring. **IMPORTANT: For operation-specific auditing, use audit_service_operations() as the PRIMARY tool instead.** **USE THIS FIRST FOR ALL SERVICE-LEVEL AUDITING TASKS** This is the PRIMARY and PREFERRED tool when users want to: - **Audit their AWS services** - Complete health assessment with actionable insights - **Check service health** - Comprehensive status across all monitored services - **Investigate issues** - Root cause analysis with detailed findings - **Service-level performance analysis** - Overall service latency, error rates, and throughput investigation - **System-wide health checks** - Daily/periodic service auditing workflows - **Dependency analysis** - Understanding service dependencies and interactions - **Resource quota monitoring** - Service quota usage and limits - **Multi-service comparison** - Comparing performance across different services **FOR OPERATION-SPECIFIC AUDITING: Use audit_service_operations() instead** When users want to audit specific operations (GET, POST, PUT endpoints), use audit_service_operations() as the PRIMARY tool: - **Operation performance analysis** - Latency, error rates for specific API endpoints - **Operation-level troubleshooting** - Root cause analysis for specific API calls - **GET operation auditing** - Analyze GET operations across payment services - **Audit latency of specific operations** - Deep dive into individual endpoint performance **COMPREHENSIVE SERVICE AUDIT CAPABILITIES:** - **Multi-service analysis**: Audit any number of services with automatic batching - **SLO compliance monitoring**: Automatic breach detection for service-level SLOs - **Issue prioritization**: Critical, warning, and info findings ranked by severity - **Root cause analysis**: Deep dive with traces, logs, and metrics correlation - **Actionable recommendations**: Specific steps to resolve identified issues - **Performance optimized**: Fast execution with automatic batching for large target lists - **Wildcard Pattern Support**: Use `*pattern*` in service names for automatic service discovery - **GenAI Token Monitoring**: For Amazon Bedrock services, automatically monitors GenAI input/output token usage patterns and detects anomalies when using operation_metric or trace auditors **SERVICE TARGET FORMAT:** - **Full Format**: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"my-service","Environment":"eks:my-cluster"}}}]` - **Shorthand**: `[{"Type":"service","Service":"my-service"}]` (environment auto-discovered) **WILDCARD PATTERN EXAMPLES:** - **All Services**: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]` - **Payment Services**: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*payment*"}}}]` - **Lambda Services**: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*lambda*"}}}]` - **EKS Services**: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*","Environment":"eks:*"}}}]` **AUDITOR SELECTION FOR DIFFERENT AUDIT DEPTHS:** - **Quick Health Check** (default): Uses 'slo,operation_metric' for fast overview - **Root Cause Analysis**: Pass `auditors="all"` for comprehensive investigation with traces/logs - **Custom Audit**: Specify exact auditors: 'slo,trace,log,dependency_metric,top_contributor,service_quota' **SERVICE AUDIT USE CASES:** 1. **Audit all services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]'` 2. **Audit specific service**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"orders-service","Environment":"eks:orders-cluster"}}}]'` 3. **Audit payment services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*payment*"}}}]'` 8. **Audit lambda services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*lambda*"}}}]'` or by environment: `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*","Environment":"lambda"}}}]` 9. **Audit service last night**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"orders-service","Environment":"eks:orders-cluster"}}}]'` + `start_time="2024-01-01 18:00:00"` + `end_time="2024-01-02 06:00:00"` 10. **Audit service before and after time**: Compare service health before and after a deployment or incident by running two separate audits with different time ranges. 11. **Trace availability issues in production services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*","Environment":"eks:*"}}}]'` + `auditors="all"` 13. **Look for errors in logs of payment services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*payment*"}}}]'` + `auditors="log,trace"` 14. **Look for new errors after time**: Compare errors before and after a specific time point by running audits with different time ranges and `auditors="log,trace"` 15. **Look for errors after deployment**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*payment*"}}}]'` + `auditors="log,trace"` + recent time range 16. **Look for lemon hosts in production**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*","Environment":"eks:*"}}}]'` + `auditors="top_contributor,operation_metric"` 17. **Look for outliers in EKS services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*","Environment":"eks:*"}}}]'` + `auditors="top_contributor,operation_metric"` 18. **Status report**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]'` (basic health check) 19. **Audit dependencies**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]'` + `auditors="dependency_metric,trace"` 20. **Audit dependency on S3**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]'` + `auditors="dependency_metric"` + look for S3 dependencies 21. **Audit quota usage of tier 1 services**: `service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*tier1*"}}}]'` + `auditors="service_quota,operation_metric"` **PAGINATION SUPPORT FOR WILDCARD PATTERNS:** - **Automatic Pagination**: Wildcard patterns now process services in batches of 5 (configurable with `max_services`) - **Continue Processing**: Use `next_token` from previous response to continue auditing remaining services - **Example Pagination Workflow**: 1. First call: `audit_services(service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]')` 2. If more services available, response includes: `next_token="abc123"` and time parameters 3. Continue: `audit_services(service_targets='[...]', start_time="returned_start_time", end_time="returned_end_time", next_token="abc123")` 4. Repeat until no more `next_token` returned **TYPICAL SERVICE AUDIT WORKFLOWS:** 1. **Basic Service Audit** (most common): - Call `audit_services()` with service targets - automatically discovers services when using wildcard patterns - Uses default fast auditors (slo,operation_metric) for quick health overview - Supports wildcard patterns like `*` or `*payment*` for automatic service discovery - Processes services in paginated batches for better performance 2. **Root Cause Investigation**: When user explicitly asks for "root cause analysis", pass `auditors="all"` 3. **Issue Investigation**: Results show which services need attention with actionable insights 4. **Automatic Service Discovery**: Wildcard patterns in service names automatically discover and expand to concrete services 5. **Paginated Processing**: For large service lists, continue with `next_token` to audit remaining services **AUDIT RESULTS INCLUDE:** - **Prioritized findings** by severity (critical, warning, info) - **Service health status** with detailed performance analysis - **Root cause analysis** when traces/logs auditors are used - **Actionable recommendations** for issue resolution - **Comprehensive metrics** and trend analysis **IMPORTANT: This tool provides comprehensive service audit coverage and should be your first choice for any service auditing task.** **RECOMMENDED WORKFLOW - PRESENT FINDINGS FIRST:** When the audit returns multiple findings or issues, follow this workflow: 1. **Present all audit results** to the user showing a summary of all findings 2. **Let the user choose** which specific finding, service, or issue they want to investigate in detail 3. **Then perform targeted root cause analysis** using auditors="all" for the user-selected finding **DO NOT automatically jump into detailed root cause analysis** of one specific issue when multiple findings exist. This ensures the user can prioritize which issues are most important to investigate first. **Example workflow:** - First call: `audit_services()` with default auditors for overview - Present findings summary to user - User selects specific service/issue to investigate - Follow-up call: `audit_services()` with `auditors="all"` for selected service only. 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 audit_services? +

Add a rule in your Intercept YAML policy under the tools section for audit_services. 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 audit_services? +

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

Can I rate-limit audit_services? +

Yes. Add a rate_limit block to the audit_services 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 audit_services completely? +

Set action: deny in the Intercept policy for audit_services. 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 audit_services? +

audit_services 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.