Get all IAM roles that can be assumed by a specific AWS service. This tool retrieves all IAM roles in your AWS account that have a trust relationship with the specified service. It helps you identify which roles can be used for services like Glue jobs, EMR clusters, or Athena queries, making it ...
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 call get_roles_for_service to retrieve information from Amazon Data Processing MCP Server without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_roles_for_service only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_roles_for_service:
rules:
- action: allowSee the full Amazon Data Processing MCP Server policy for all 36 tools.
Agents calling read-class tools like get_roles_for_service have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Get all IAM roles that can be assumed by a specific AWS service. This tool retrieves all IAM roles in your AWS account that have a trust relationship with the specified service. It helps you identify which roles can be used for services like Glue jobs, EMR clusters, or Athena queries, making it easier to select the appropriate role when creating these resources. ## Service Types Common service types include: - **glue**: AWS Glue service (glue.amazonaws.com) - **emr**: Amazon EMR service (elasticmapreduce.amazonaws.com) - **athena**: Amazon Athena service (athena.amazonaws.com) - You can also specify other AWS service principals ## Response Information The response includes a list of roles that can be assumed by the specified service, with details such as role name, ARN, description, creation date, and the full assume role policy document. ## Usage Tips - Use this tool to find existing roles before creating new ones - Verify that roles have the necessary permissions for your use case - For Glue jobs, look for roles with AWSGlueServiceRole or similar policies - For EMR clusters, look for roles with AmazonElasticMapReduceRole or similar policies - For Athena queries, look for roles with AmazonAthenaFullAccess or similar policies Args: ctx: The MCP context service_type: Type of data processing service Returns: CallToolResult: List of roles that can be assumed by the specified service. It is categorised as a Read tool in the Amazon Data Processing MCP Server MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_roles_for_service. 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.
get_roles_for_service is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_roles_for_service 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 get_roles_for_service. 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.
get_roles_for_service 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.