Manage AWS EMR Serverless applications with comprehensive control over application lifecycle. This tool provides operations for managing Amazon EMR Serverless applications, including creating, configuring, monitoring, updating, starting, stopping, and deleting applications. ## Requirements - Th...
High parameter count (23 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_applications 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_applications 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_applications:
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_applications 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 applications with comprehensive control over application lifecycle. This tool provides operations for managing Amazon EMR Serverless applications, including creating, configuring, monitoring, updating, starting, stopping, and deleting applications. ## Requirements - The server must be run with the `--allow-write` flag for create-application, update-application, delete-application, start-application, and stop-application operations - Appropriate AWS permissions for EMR Serverless application operations ## Operations - **create-application**: Create a new EMR Serverless application - **get-application**: Get detailed information about a specific application - **update-application**: Update an existing application configuration - **delete-application**: Delete an application (must be in stopped or created state) - **list-applications**: List all EMR Serverless applications with optional filtering - **start-application**: Start a specified application and initialize capacity - **stop-application**: Stop a specified application and release capacity ## Example ``` # Create a basic EMR Serverless Spark application { 'operation': 'create-application', 'name': 'MySparkApp', 'release_label': 'emr-7.0.0', 'type': 'Spark', 'client_token': 'unique-token-123', 'auto_start_configuration': {'enabled': True}, 'auto_stop_configuration': {'enabled': True, 'idleTimeoutMinutes': 15}, } ``` ## Usage Tips - Use list-applications to find application IDs before performing operations on specific applications - Check application state before performing operations that require specific states - For large result sets, use pagination with next_token parameter - Applications must be stopped before they can be deleted Args: ctx: MCP context operation: Operation to perform application_id: ID of the EMR Serverless application name: Name of the EMR Serverless application release_label: The Amazon EMR release associated with the application type: The type of application, such as Spark or Hive client_token: The client idempotency token initial_capacity: The capacity to initialize when the application is created/updated maximum_capacity: The maximum capacity to allocate tags: The tags assigned to the application auto_start_configuration: The configuration for automatic start auto_stop_configuration: The configuration for automatic stop network_configuration: The network configuration for VPC connectivity architecture: The CPU architecture of the application image_configuration: The image configuration for all worker types worker_type_specifications: The worker type specifications runtime_configuration: The Configuration specifications monitoring_configuration: The monitoring configuration interactive_configuration: The interactive configuration scheduler_configuration: The scheduler configuration identity_center_configuration: The IAM Identity Center configuration next_token: The token for pagination max_results: The maximum number of results states: Filter for application states 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_applications. 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_applications 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_applications 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_applications. 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_applications 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.