Manage AWS Glue ETL jobs and job runs with both read and write operations. This tool provides comprehensive operations for managing AWS Glue ETL jobs and job runs, including creating, updating, retrieving, listing, starting, stopping, and monitoring jobs. ## Requirements - The server must be ru...
High parameter count (16 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_glue_jobs 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_glue_jobs 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_glue_jobs:
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_glue_jobs 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 Glue ETL jobs and job runs with both read and write operations. This tool provides comprehensive operations for managing AWS Glue ETL jobs and job runs, including creating, updating, retrieving, listing, starting, stopping, and monitoring jobs. ## Requirements - The server must be run with the `--allow-write` flag for create-job, delete-job, update-job, start-job-run, stop-job-run, and batch-stop-job-run operations - Appropriate AWS permissions for Glue ETL job operations ## Job Operations - **create-job**: Create a new ETL job in AWS Glue - **delete-job**: Delete an existing ETL job from AWS Glue - **get-job**: Retrieve detailed information about a specific job - **get-jobs**: List all jobs in your AWS Glue account - **update-job**: Update an existing job's properties - **start-job-run**: Start a job run using a job name ## Job Run Operations - **stop-job-run**: Stop a job run using a job name and run ID - **get-job-run**: Retrieve detailed information about a specific job run - **get-job-runs**: List all job runs for a specific job - **batch-stop-job-run**: Stop one or more running jobs ## Usage Tips - Job names must be unique within your AWS account and region - Create a script required by the customer and push the script to a customer S3 Location. Ask for S3 Location if not provided. - Verify if the IAM role used has glue trusted entities in the role if not update the role or create a new one - Job definitions should include command, role, and other required parameters - As rule of thumb use Glue Version 5.0 or latest to create jobs ## Examples ``` # Create a new Spark ETL job { 'operation': 'create-job', 'job_name': 'my-etl-job', 'job_definition': { 'Role': 'arn:aws:iam::123456789012:role/GlueETLRole', 'Command': { 'Name': 'glueetl', 'ScriptLocation': 's3://my-bucket/scripts/etl-script.py', }, 'GlueVersion': '5.0', 'MaxRetries': 2, 'Timeout': 120, 'WorkerType': 'G.1X', 'NumberOfWorkers': 5, }, } # Start a job run { 'operation': 'start-job-run', 'job_name': 'my-etl-job', 'worker_type': 'G.1X', 'number_of_workers': 5, } # Get details of a specific job run { 'operation': 'get-job-run', 'job_name': 'my-etl-job', 'job_run_id': 'jr_1234567890abcdef0', } ``` Args: ctx: MCP context operation: Operation to perform job_name: Name of the job job_definition: Job definition for create-job and update-job operations job_run_id: Job run ID for get-job-run, stop-job-run operations, or to retry for start-job-run operation job_run_ids: List of job run IDs for batch-stop-job-run operation job_arguments: Job arguments for start-job-run operation max_results: Maximum number of results to return for get-jobs or get-job-runs operations next_token: Pagination token for get-jobs or get-job-runs operations worker_type: Worker type for start-job-run operation number_of_workers: Number of workers for start-job-run operation max_capacity: Maximum capacity in DPUs for start-job-run operation timeout: Timeout in minutes for start-job-run operation security_configuration: Security configuration name for start-job-run operation execution_class: Execution class for start-job-run operation job_run_queuing_enabled: Whether job run queuing is enabled for start-job-run operation predecessors_included: Whether to include predecessor runs in get-job-run operation 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_glue_jobs. 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_glue_jobs 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_glue_jobs 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_glue_jobs. 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_glue_jobs 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.