OPERATION DISCOVERY TOOL - For operation inventory only. Use audit_services() as PRIMARY tool for operation auditing. **IMPORTANT: For operation auditing and performance analysis, use audit_services() as the PRIMARY tool instead.** **CRITICAL LIMITATION: This tool only discovers operations that...
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_service_operations 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_service_operations 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_service_operations:
rules:
- action: allowSee the full CloudWatch Application Signals MCP Server policy for all 22 tools.
Agents calling read-class tools like list_service_operations 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.
OPERATION DISCOVERY TOOL - For operation inventory only. Use audit_services() as PRIMARY tool for operation auditing. **IMPORTANT: For operation auditing and performance analysis, use audit_services() as the PRIMARY tool instead.** **CRITICAL LIMITATION: This tool only discovers operations that have been ACTIVELY INVOKED in the specified time window.** - **Maximum time window: 24 hours** (Application Signals limitation for operation discovery) - **No results = No operation invocations** in the time window (operations exist but weren't called) - **Empty results do NOT mean operations don't exist** - they may just be inactive - **For comprehensive operation analysis regardless of recent activity, use audit_services() instead** **RECOMMENDED WORKFLOW FOR OPERATION AUDITING:** 1. **Use audit_services() FIRST** for comprehensive operation discovery AND performance analysis 2. **Only use this tool** if you need a simple operation inventory of RECENTLY ACTIVE operations 3. **audit_services() is more comprehensive** - it discovers operations AND provides performance insights even for inactive operations **What this tool provides:** - Basic operation inventory (names and available metric types) for RECENTLY INVOKED operations only - Operation count and categorization (GET, POST, etc.) for active operations - Time range for discovery (max 24 hours) **What this tool does NOT provide:** - Operations that exist but weren't invoked in the time window - Operation performance analysis - Latency, error rate, or fault analysis - Root cause analysis - Actionable recommendations **For comprehensive operation auditing, use audit_services() instead:** ``` audit_services( service_targets='[{"Type":"service","Data":{"Service":{"Type":"Service","Name":"your-service"}}}]', auditors='all', ) ``` **OPERATION DISCOVERY USE CASES (when audit_services is not sufficient):** 1. **Active operation inventory**: When you only need recently invoked operation names without performance data 2. **Traffic pattern analysis**: To see which operations are currently being used 3. **Quick active operation count**: To understand current operation activity of a service **RECOMMENDED WORKFLOW:** 1. **Use audit_services() FIRST** for comprehensive operation discovery and analysis 2. **Only use this tool** for basic inventory of recently active operations if audit_services() provides too much detail This tool provides basic operation discovery for ACTIVE operations only, but audit_services() is the primary tool for comprehensive operation auditing, performance analysis, and operation insights regardless of recent activity.. 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_service_operations. 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_service_operations 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_service_operations 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_service_operations. 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_service_operations 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.