OPTIONAL TOOL for service discovery - audit_services() can automatically discover services using wildcard patterns. **IMPORTANT: For service auditing and operation analysis, use audit_services() as the PRIMARY tool instead.** **WHEN TO USE THIS TOOL:** - Getting a detailed overview of all monit...
Admin/system-level operation
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 list_monitored_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.
Even though list_monitored_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.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
list_monitored_services:
rules:
- action: allowSee the full CloudWatch Application Signals MCP Server policy for all 22 tools.
Agents calling read-class tools like list_monitored_services 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.
OPTIONAL TOOL for service discovery - audit_services() can automatically discover services using wildcard patterns. **IMPORTANT: For service auditing and operation analysis, use audit_services() as the PRIMARY tool instead.** **WHEN TO USE THIS TOOL:** - Getting a detailed overview of all monitored services in your environment - Discovering specific service names and environments for manual audit target construction - Understanding the complete service inventory before targeted analysis - When you need detailed service attributes beyond what wildcard expansion provides **RECOMMENDED WORKFLOW FOR SERVICE AND OPERATION AUDITING:** 1. **Use audit_services() FIRST** with wildcard patterns for comprehensive service discovery AND analysis 2. **Only use this tool** if you need basic service inventory without performance analysis 3. **audit_services() is more comprehensive** - it discovers services AND provides performance insights **AUTOMATIC SERVICE DISCOVERY IN AUDIT:** The `audit_services()` tool automatically discovers services when you use wildcard patterns: - `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]` - Audits all services - `[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*payment*"}}}]` - Audits services with "payment" in the name **What this tool provides:** - Basic service inventory (names, types, environments) - Service count and categorization - Key attributes for manual target construction **What this tool does NOT provide:** - Service performance analysis - Operation discovery and analysis - Root cause analysis - Actionable recommendations **For comprehensive service auditing, use audit_services() instead:** ``` audit_services( service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"*"}}}]', auditors='all', ) ``` Returns a formatted list showing: - Service name and type - Key attributes (Name, Environment, Platform, etc.) - Total count of services **NOTE**: For operation auditing, use audit_services() as the primary tool instead of get_service_detail() or list_service_operations().. 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 list_monitored_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.
list_monitored_services 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 list_monitored_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.
Set action: deny in the Intercept policy for list_monitored_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.
list_monitored_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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.