Describe a computation model execution summary in AWS IoT SiteWise. This tool intelligently determines whether to use resolve parameters based on the computation model configuration: - For Asset Model Level Configuration: Uses resolve parameters if provided to get execution summary for specific ...
Single-target operation
Part of the AWS IoT SiteWise MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call describe_computation_model_execution_summary to retrieve information from AWS IoT SiteWise 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 describe_computation_model_execution_summary 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:
describe_computation_model_execution_summary:
rules:
- action: allowSee the full AWS IoT SiteWise MCP Server policy for all 72 tools.
Agents calling read-class tools like describe_computation_model_execution_summary 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.
Describe a computation model execution summary in AWS IoT SiteWise. This tool intelligently determines whether to use resolve parameters based on the computation model configuration: - For Asset Model Level Configuration: Uses resolve parameters if provided to get execution summary for specific assets - For Asset Level Configuration: Ignores resolve parameters as they're not needed (already tied to specific assets) **Smart Optimization**: If you know the configuration type, provide it via the `configuration_type` parameter to avoid an additional API call to describe_computation_model for type detection. Args: computation_model_id: The ID of the computation model (required, must be in UUID format) region: AWS region (default: us-east-1) resolve_to_resource_id: Optional ID of the resolved resource (only used for asset model level configurations) resolve_to_resource_type: Optional type of the resolved resource (ASSET, only used for asset model level configurations) configuration_type: Optional configuration type hint to avoid auto-detection API call. Use 'asset_model_level' or 'asset model level configuration' for Asset Model Level, or 'asset_level' or 'asset level configuration' for Asset Level. If not provided, the function will auto-detect by calling describe_computation_model. Returns: Dictionary containing the computation model execution summary and configuration type information. Example: # Auto-detect configuration type (makes additional API call) result = describe_computation_model_execution_summary( '12345678-1234-1234-1234-123456789012' ) # Optimized: Provide known configuration type to skip auto-detection result = describe_computation_model_execution_summary( computation_model_id='12345678-1234-1234-1234-123456789012', configuration_type='asset_model_level' ) # Asset model level configuration resolved to a specific asset result = describe_computation_model_execution_summary( computation_model_id='12345678-1234-1234-1234-123456789012', resolve_to_resource_id='87654321-4321-4321-4321-210987654321', resolve_to_resource_type='ASSET', configuration_type='asset_model_level' # Skip auto-detection for better performance ) # Asset level configuration (resolve parameters will be ignored) result = describe_computation_model_execution_summary( computation_model_id='12345678-1234-1234-1234-123456789012', configuration_type='asset_level' # Skip auto-detection for better performance ) Performance Tips: - Use configuration_type parameter when you know the computation model type to avoid extra API calls - For Asset Model Level configurations, consider providing resolve parameters for specific asset context - For Asset Level configurations, resolve parameters are automatically ignored (already tied to specific assets). It is categorised as a Read tool in the AWS IoT SiteWise 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 describe_computation_model_execution_summary. 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.
describe_computation_model_execution_summary 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 describe_computation_model_execution_summary 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 describe_computation_model_execution_summary. 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.
describe_computation_model_execution_summary 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.