ecs_troubleshooting_tool

// WHEN AI AGENTS USE THIS TOOL

AI agents invoke ecs_troubleshooting_tool to trigger processes or run actions in Amazon ECS 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.

// WHY ENFORCE A POLICY ON ECS_TROUBLESHOOTING_TOOL

ecs_troubleshooting_tool 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.

// RECOMMENDED POLICY

Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.

amazon-ecs-mcp-server.yaml

tools:
  ecs_troubleshooting_tool:
    rules:
      - action: allow
        rate_limit:
          max: 10
          window: 60
        validate:
          required_args: true

See the full Amazon ECS MCP Server policy for all 10 tools.

// DETAILS

Tool Name ecs_troubleshooting_tool

Category Execute

MCP Server Amazon ECS MCP Server MCP Server

Risk Level High

// MORE AMAZON ECS MCP SERVER TOOLS

Destructive delete_app Destructive delete_ecs_infrastructure Execute build_and_push_image_to_ecr Execute containerize_app Execute ecs_resource_management Execute wait_for_service_ready Write create_ecs_infrastructure Read get_deployment_status

View all 10 tools →

// WHAT CAN GO WRONG

Agents calling execute-class tools like ecs_troubleshooting_tool have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER EXECUTE TOOLS ACROSS MCP SERVERS

Other tools in the Execute risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

Atv build_stake_tx Atv build_unstake_tx Acdp start_local Pentagonal pentagonal_audit Pentagonal pentagonal_compile ACR — Agent Composition Records orient_me

// IN CONTEXT OF HIGH RISK

ecs_troubleshooting_tool is one of the high-risk operations in Amazon ECS 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.

// RELATED READING

// FAQ

What does the ecs_troubleshooting_tool tool do? +

ECS troubleshooting tool with multiple diagnostic actions. This tool provides access to all ECS troubleshooting operations through a single interface. Use the 'action' parameter to specify which troubleshooting operation to perform. ## Available Actions and Parameters: ### 1. get_ecs_troubleshooting_guidance Initial assessment and data collection - Required: ecs_cluster_name - Optional: ecs_service_name (Name of the ECS Service to troubleshoot), symptoms_description (Description of symptoms experienced by the user) - Example: action="get_ecs_troubleshooting_guidance", parameters={"ecs_cluster_name": "my-cluster", "ecs_service_name": "my-service", "symptoms_description": "ALB returning 503 errors"} ### 2. fetch_cloudformation_status Infrastructure-level diagnostics for CloudFormation Stacks - Required: cfn_stack_name - Example: action="fetch_cloudformation_status", parameters={"cfn_stack_name": "my-app-stack"} ### 3. fetch_service_events Service-level diagnostics for ECS Services - Required: ecs_cluster_name, ecs_service_name - Optional: time_window (Time window in seconds to look back for events (default: 3600)), start_time (Explicit start time for the analysis window (UTC, takes precedence over time_window if provided)), end_time (Explicit end time for the analysis window (UTC, defaults to current time if not provided)) - Example: action="fetch_service_events", parameters={"ecs_cluster_name": "my-cluster", "ecs_service_name": "my-service", "time_window": 7200} ### 4. fetch_task_failures Task-level diagnostics for ECS Task failures - Required: ecs_cluster_name - Optional: time_window (Time window in seconds to look back for failures (default: 3600)), start_time (Explicit start time for the analysis window (UTC, takes precedence over time_window if provided)), end_time (Explicit end time for the analysis window (UTC, defaults to current time if not provided)) - Example: action="fetch_task_failures", parameters={"ecs_cluster_name": "my-cluster", "time_window": 3600} ### 5. fetch_task_logs Application-level diagnostics through CloudWatch Logs - Required: ecs_cluster_name - Optional: ecs_task_id (Specific ECS Task ID to retrieve logs for), time_window (Time window in seconds to look back for logs (default: 3600)), filter_pattern (CloudWatch Logs filter pattern), start_time (Explicit start time for the analysis window (UTC, takes precedence over time_window if provided)), end_time (Explicit end time for the analysis window (UTC, defaults to current time if not provided)) - Example: action="fetch_task_logs", parameters={"ecs_cluster_name": "my-cluster", "filter_pattern": "ERROR", "time_window": 1800} ### 6. detect_image_pull_failures Specialized tool for detecting container image pull failures - Required: None (but at least one valid parameter combination must be provided) - Valid combinations: ecs_cluster_name+ecs_service_name, ecs_cluster_name+ecs_task_id, cfn_stack_name, family_prefix - Optional: ecs_cluster_name, ecs_service_name, cfn_stack_name, family_prefix, ecs_task_id - Example: action="detect_image_pull_failures", parameters={"ecs_cluster_name": "my-cluster", "ecs_service_name": "my-service"} ### 7. fetch_network_configuration Network-level diagnostics for ECS deployments - Required: ecs_cluster_name - Optional: vpc_id (Specific VPC ID to analyze) - Example: action="fetch_network_configuration", parameters={"ecs_cluster_name": "my-cluster", "vpc_id": "vpc-12345678"} ## Resource Discovery: If you don't know the cluster or service names, use `ecs_resource_management` tool first: # List all clusters ecs_resource_management(api_operation="ListClusters") # List services in a cluster ecs_resource_management(api_operation="ListServices", api_params={"cluster": "my-cluster"}) # Get detailed cluster information ecs_resource_management(api_operation="DescribeClusters", api_params={"clusters": ["my-cluster"]}) ## Quick Usage Examples: ``` # Initial assessment and data collection action: "get_ecs_troubleshooting_guidance" parameters: {"ecs_cluster_name": "my-cluster", "symptoms_description": "ALB returning 503 errors"} # Infrastructure-level diagnostics for CloudFormation Stacks action: "fetch_cloudformation_status" parameters: {"cfn_stack_name": "my-app-stack"} # Service-level diagnostics for ECS Services action: "fetch_service_events" parameters: {"ecs_cluster_name": "my-cluster", "ecs_service_name": "my-service", "time_window": 7200} # Task-level diagnostics for ECS Task failures action: "fetch_task_failures" parameters: {"ecs_cluster_name": "my-cluster", "time_window": 3600} # Application-level diagnostics through CloudWatch Logs action: "fetch_task_logs" parameters: {"ecs_cluster_name": "my-cluster", "filter_pattern": "ERROR", "time_window": 1800} # Specialized tool for detecting container image pull failures action: "detect_image_pull_failures" parameters: {"ecs_cluster_name": "my-cluster", "ecs_service_name": "my-service"} # Network-level diagnostics for ECS deployments action: "fetch_network_configuration" parameters: {"ecs_cluster_name": "my-cluster", "vpc_id": "vpc-12345678"} ``` Parameters: action: The troubleshooting action to perform (see available actions above) parameters: Action-specific parameters (see parameter specifications above) Returns: Results from the selected troubleshooting action. It is categorised as a Execute tool in the Amazon ECS MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ecs_troubleshooting_tool? +

Add a rule in your Intercept YAML policy under the tools section for ecs_troubleshooting_tool. 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.

What risk level is ecs_troubleshooting_tool? +

ecs_troubleshooting_tool is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ecs_troubleshooting_tool? +

Yes. Add a rate_limit block to the ecs_troubleshooting_tool 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.

How do I block ecs_troubleshooting_tool completely? +

Set action: deny in the Intercept policy for ecs_troubleshooting_tool. 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.

What MCP server provides ecs_troubleshooting_tool? +

ecs_troubleshooting_tool 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.

ecs_troubleshooting_tool

Let agents act without letting them run wild.