Gets the status of an ECS deployment and returns the ALB URL. This tool checks the status of your ECS deployment and provides information about the Service, Tasks, and the Application Load Balancer URL for accessing your application. USAGE INSTRUCTIONS: 1. Provide the name of your application 2...
Bulk/mass operation — affects multiple targets
Part of the Amazon ECS MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_deployment_status to retrieve information from Amazon ECS 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 get_deployment_status 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:
get_deployment_status:
rules:
- action: allowSee the full Amazon ECS MCP Server policy for all 10 tools.
Agents calling read-class tools like get_deployment_status 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.
Gets the status of an ECS deployment and returns the ALB URL. This tool checks the status of your ECS deployment and provides information about the Service, Tasks, and the Application Load Balancer URL for accessing your application. USAGE INSTRUCTIONS: 1. Provide the name of your application 2. Optionally specify the ECS Cluster name if different from the application name 3. Optionally specify the CloudFormation Stack name if different from the default naming convention 4. Optionally specify the ECS Service name if different from the default naming pattern 5. The tool will return the deployment status and access URL once the deployment is complete. Poll this tool every 30 seconds till the status is active. The status information includes: - ECS Service status (active, draining, etc.) - Running Task count - Desired Task count - Application Load Balancer URL - Recent deployment events - Health check status - Custom domain and HTTPS setup guidance (when deployment is complete) Parameters: app_name: Name of the application cluster_name: Name of the ECS Cluster (optional, defaults to app_name) stack_name: Name of the CloudFormation Stack (optional, defaults to {app_name}-ecs-infrastructure) service_name: Name of the ECS Service (optional, defaults to {app_name}-service) Returns: Dictionary containing deployment status and ALB URL. It is categorised as a Read tool in the Amazon ECS 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 get_deployment_status. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon ECS MCP Server MCP server.
get_deployment_status 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 get_deployment_status 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 get_deployment_status. 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.
get_deployment_status is provided by the Amazon ECS MCP Server MCP server (awslabs.ecs-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.