Get CloudWatch metrics for a specific Application Signals service. Use this tool to: - Analyze service performance (latency, throughput) - Check error rates and reliability - View trends over time - Get both standard statistics (Average, Max) and percentiles (p99, p95) Common metric names: - 'L...
Single-target 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 query_service_metrics 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 query_service_metrics 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:
query_service_metrics:
rules:
- action: allowSee the full CloudWatch Application Signals MCP Server policy for all 22 tools.
Agents calling read-class tools like query_service_metrics 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.
Get CloudWatch metrics for a specific Application Signals service. Use this tool to: - Analyze service performance (latency, throughput) - Check error rates and reliability - View trends over time - Get both standard statistics (Average, Max) and percentiles (p99, p95) Common metric names: - 'Latency': Response time in milliseconds - 'Error': Percentage of failed requests - 'Fault': Percentage of server errors (5xx) Returns: - Summary statistics (latest, average, min, max) - Recent data points with timestamps - Both standard and percentile values when available The tool automatically adjusts the granularity based on time range: - Up to 3 hours: 1-minute resolution - Up to 24 hours: 5-minute resolution - Over 24 hours: 1-hour resolution. 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 query_service_metrics. 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.
query_service_metrics 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 query_service_metrics 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 query_service_metrics. 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.
query_service_metrics 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.