Manage AWS EMR Serverless job runs for executing data processing workloads. This tool provides operations for managing Amazon EMR Serverless job runs, including starting new jobs, monitoring execution, cancelling jobs, and accessing dashboards. ## Requirements - The server must be run with the ...
High parameter count (19 properties); Single-target operation
Part of the Amazon Data Processing MCP Server MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use manage_aws_emr_serverless_job_runs to create or modify resources in Amazon Data Processing MCP Server. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call manage_aws_emr_serverless_job_runs repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Amazon Data Processing MCP Server.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
manage_aws_emr_serverless_job_runs:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Amazon Data Processing MCP Server policy for all 36 tools.
Agents calling write-class tools like manage_aws_emr_serverless_job_runs have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Manage AWS EMR Serverless job runs for executing data processing workloads. This tool provides operations for managing Amazon EMR Serverless job runs, including starting new jobs, monitoring execution, cancelling jobs, and accessing dashboards. ## Requirements - The server must be run with the `--allow-write` flag for start-job-run and cancel-job-run operations - Application must exist and be in appropriate state for job execution - Appropriate AWS permissions for EMR Serverless job run operations ## Operations - **start-job-run**: Start a new job run on an EMR Serverless application - **get-job-run**: Get detailed information about a specific job run - **cancel-job-run**: Cancel a running job run - **list-job-runs**: List job runs for an application with optional filtering - **get-dashboard-for-job-run**: Get the dashboard URL for monitoring a job run ## Example ``` # Start a Spark job run { 'operation': 'start-job-run', 'application_id': '00f4ac4c0b27001f', 'execution_role_arn': 'arn:aws:iam::123456789012:role/EMRServerlessExecutionRole', 'job_driver': { 'sparkSubmit': { 'entryPoint': 's3://my-bucket/my-spark-job.py', 'entryPointArguments': [ '--input', 's3://my-bucket/input/', '--output', 's3://my-bucket/output/', ], 'sparkSubmitParameters': '--conf spark.executor.cores=2 --conf spark.executor.memory=4g', } }, 'name': 'MySparkJob', 'tags': {'Environment': 'Production', 'Team': 'DataEngineering'}, } ``` ## Usage Tips - Use list-job-runs to find job run IDs before performing operations on specific job runs - Check job run state before performing operations that require specific states - For large result sets, use pagination with next_token parameter - Use get-dashboard-for-job-run to get monitoring URLs for active job runs Args: ctx: MCP context for request tracking and logging operation: Operation to perform (start-job-run, get-job-run, cancel-job-run, list-job-runs, get-dashboard-for-job-run) application_id: ID of the EMR Serverless application (required for all operations) job_run_id: ID of the job run (required for get-job-run, cancel-job-run, get-dashboard-for-job-run) execution_role_arn: The execution role ARN for the job run (required for start-job-run) job_driver: The job driver configuration (required for start-job-run). Example: {"sparkSubmit": {"entryPoint": "s3://bucket/script.py"}} configuration_overrides: Configuration overrides for the job run (optional for start-job-run) tags: Tags to apply to the job run (optional for start-job-run) execution_timeout_minutes: Maximum execution time in minutes (optional for start-job-run) name: Name for the job run (optional for start-job-run) client_token: Client token for idempotency (optional for start-job-run) max_results: Maximum number of results to return (optional for list-job-runs) next_token: Token for pagination (optional for list-job-runs) created_at_after: Filter job runs created after this timestamp (optional for list-job-runs). Format: ISO 8601 created_at_before: Filter job runs created before this timestamp (optional for list-job-runs). Format: ISO 8601 states: Filter job runs by states (optional for list-job-runs). Valid states: SUBMITTED, PENDING, SCHEDULED, RUNNING, SUCCESS, FAILED, CANCELLING, CANCELLED mode: Mode for the dashboard (optional for get-dashboard-for-job-run) job_timeout_minutes: Job timeout in minutes (optional for start-job-run) retry_policy: Retry policy configuration (optional for start-job-run) attempt: Attempt number for dashboard (optional for get-dashboard-for-job-run) 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_serverless_job_runs. 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_serverless_job_runs 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_serverless_job_runs 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_serverless_job_runs. 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_serverless_job_runs 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.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.