Execute an inference action for anomaly detection models in AWS IoT SiteWise. This is a specialized function for executing inference actions on anomaly detection computation models. It handles the specific payload format required for inference operations and delegates to the execute_action funct...
High parameter count (11 properties)
Part of the AWS IoT SiteWise MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents invoke execute_inference_action to trigger processes or run actions in AWS IoT SiteWise MCP Server. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
execute_inference_action can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. Intercept enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
tools:
execute_inference_action:
rules:
- action: allow
rate_limit:
max: 10
window: 60
validate:
required_args: trueSee the full AWS IoT SiteWise MCP Server policy for all 72 tools.
Agents calling execute-class tools like execute_inference_action have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
execute_inference_action is one of the high-risk operations in AWS IoT SiteWise MCP Server. For the full severity-focused view — only the high-risk tools with their recommended policies — see the breakdown for this server, or browse all high-risk tools across every MCP server.
Execute an inference action for anomaly detection models in AWS IoT SiteWise. This is a specialized function for executing inference actions on anomaly detection computation models. It handles the specific payload format required for inference operations and delegates to the execute_action function. Note: Get the inference_action_definition_id from describe_computation_model response's actionDefinitions array (actionType: "AWS/ANOMALY_DETECTION_INFERENCE"). Args: inference_action_definition_id: The ID of the inference action definition (required) inference_mode: The inference mode - START or STOP (required) target_resource: Resource containing computationModelId (required, computationModelId must be in UUID format) region: AWS region (default: us-east-1) # START mode parameters: data_upload_frequency: Data upload frequency (PT5M, PT10M, PT15M, PT30M, PT1H, PT2H, PT3H, PT4H, PT5H, PT6H, PT7H, PT8H, PT9H, PT10H, PT11H, PT12H, PT1D) (REQUIRED for START mode) data_delay_offset_in_minutes: Delay offset in minutes (0-60) (optional for START mode only, not allowed for STOP mode) target_model_version: Model version to activate (positive integer) (optional for START mode only, not allowed for STOP mode) weekly_operating_window: Flexible scheduling window with day-to-time range mappings (optional for START mode) Dict with day names (monday-sunday) as keys and list of time ranges as values Time ranges in 24-hour format "HH:MM-HH:MM" (e.g., {"monday": ["10:00-11:00", "13:00-15:00"]}) inference_time_zone: IANA timezone identifier for inference scheduling (optional for START mode) Uses Time Zone Database maintained by IANA to align inference with local working hours Examples: "America/Chicago", "Europe/London", "UTC", "GMT+05:30" # STOP mode parameters: # No additional parameters required or accepted for STOP mode # Common optional parameters: client_token: Optional unique identifier for idempotent requests resolve_to: Optional detailed resource this action resolves to Must contain assetId if provided Returns: Dictionary containing the action execution response. Example: # Start inference on a computation model with all optional parameters result = execute_inference_action( inference_action_definition_id='12345678-1234-1234-1234-123456789012', inference_mode='START', target_resource={'computationModelId': '87654321-4321-4321-4321-210987654321'}, data_upload_frequency='PT15M', data_delay_offset_in_minutes=30, target_model_version=3, weekly_operating_window={ "monday": ["10:00-11:00", "13:00-15:00"], "tuesday": ["11:00-13:00"] }, inference_time_zone='America/Chicago', resolve_to={'assetId': '11111111-1111-1111-1111-111111111111'} ) # Stop inference result = execute_inference_action( inference_action_definition_id='12345678-1234-1234-1234-123456789012', inference_mode='STOP', target_resource={'computationModelId': '87654321-4321-4321-4321-210987654321'} ). It is categorised as a Execute tool in the AWS IoT SiteWise MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Add a rule in your Intercept YAML policy under the tools section for execute_inference_action. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS IoT SiteWise MCP Server MCP server.
execute_inference_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the execute_inference_action 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 execute_inference_action. 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.
execute_inference_action is provided by the AWS IoT SiteWise MCP Server MCP server (awslabs.aws-iot-sitewise-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.