manage_aws_emr_ec2_steps

Manage AWS EMR EC2 steps for processing data on EMR clusters. This tool provides comprehensive operations for managing EMR steps, which are units of work submitted to an EMR cluster for execution. Steps typically consist of Hadoop or Spark jobs that process and analyze data. ## Requirements - The server must be run with the `--allow-write` flag for add-steps and cancel-steps operations - Appropriate AWS permissions for EMR step operations ## Operations - **add-steps**: Add new steps to a running EMR cluster (max 256 steps per job flow) - **cancel-steps**: Cancel pending or running steps on an EMR cluster (EMR 4.8.0+ except 5.0.0) - **describe-step**: Get detailed information about a specific step's configuration and status - **list-steps**: List and filter steps for an EMR cluster with pagination support ## Usage Tips - Each step consists of a JAR file, its main class, and arguments - Steps are executed in the order listed and must exit with zero code to be considered complete - For cancel-steps, you can specify SEND_INTERRUPT (default) or TERMINATE_PROCESS as cancellation option - When listing steps, filter by step states: PENDING, CANCEL_PENDING, RUNNING, COMPLETED, CANCELLED, FAILED, INTERRUPTED - For large result sets, use pagination with marker parameter ## Example ``` # Add a Spark step to process data { 'operation': 'add-steps', 'cluster_id': 'j-2AXXXXXXGAPLF', 'steps': [ { 'Name': 'Spark Data Processing', 'ActionOnFailure': 'CONTINUE', 'HadoopJarStep': { 'Jar': 'command-runner.jar', 'Args': [ 'spark-submit', '--class', 'com.example.SparkProcessor', 's3://mybucket/myapp.jar', 'arg1', 'arg2', ], }, } ], } ``` Args: ctx: MCP context operation: Operation to perform cluster_id: ID of the EMR cluster step_id: ID of the EMR step step_ids: List of EMR step IDs steps: List of steps to add to the cluster step_states: The step state filters to apply when listing steps marker: The pagination token for list-steps operation step_cancellation_option: Option for canceling steps (SEND_INTERRUPT or TERMINATE_PROCESS) Returns: Union of response types specific to the operation performed. It is categorised as a Write tool in the Amazon Data Processing MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

Add a rule in your Intercept YAML policy under the tools section for manage_aws_emr_ec2_steps. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Amazon Data Processing MCP Server MCP server.

manage_aws_emr_ec2_steps is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Yes. Add a rate_limit block to the manage_aws_emr_ec2_steps 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 manage_aws_emr_ec2_steps. 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.

manage_aws_emr_ec2_steps is provided by the Amazon Data Processing MCP Server MCP server (awslabs.aws-dataprocessing-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.