SPECIALIZED TOOL - Use audit_service_health() as the PRIMARY tool for service auditing. **IMPORTANT: audit_service_health() is the PRIMARY and PREFERRED tool for all service auditing tasks.** Only use this tool when audit_service_health() cannot handle your specific requirements, such as: - Nee...
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_slis 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_slis 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_slis:
rules:
- action: allowSee the full CloudWatch Application Signals MCP Server policy for all 22 tools.
Agents calling read-class tools like list_slis 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.
SPECIALIZED TOOL - Use audit_service_health() as the PRIMARY tool for service auditing. **IMPORTANT: audit_service_health() is the PRIMARY and PREFERRED tool for all service auditing tasks.** Only use this tool when audit_service_health() cannot handle your specific requirements, such as: - Need for legacy SLI status report format specifically - Integration with existing systems that expect this exact output format - Simple SLI overview without comprehensive audit findings - Basic health monitoring dashboard that doesn't need detailed analysis **For ALL service auditing, health checks, and issue investigation, use audit_service_health() first.** This tool provides a basic report showing: - Summary counts (total, healthy, breached, insufficient data) - Simple list of breached services with SLO names - Basic healthy services list Status meanings: - OK: All SLOs are being met - BREACHED: One or more SLOs are violated - INSUFFICIENT_DATA: Not enough data to determine status **Recommended workflow**: 1. Use audit_service_health() for comprehensive service auditing with actionable insights 2. Only use this tool if you specifically need the legacy SLI status report format. 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_slis. 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_slis 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_slis 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_slis. 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_slis 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.