list_roles

A read tool on the AWS MCP server.

SERVERAWS SOURCE@awslabs/mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity verified Pull the record →

This record as markdown: /tools/aws/list-roles.md

WHAT IT DOES

What list_roles does on AWS

AI agents call list_roles to retrieve information from AWS without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why list_roles is rated Low

The 'list' prefix strongly suggests data retrieval without side effects. Given the AWS context (evident from sibling tools like attach_user_policy, add_user_to_group) and the absence of mutating language (create, delete, update, modify), this tool retrieves or enumerates existing roles. While sensitive data may be returned (role names, ARNs), the operation itself is read-only and low risk.

From the tool's definition Tool name 'list_roles' indicates a query/retrieval operation. The empty description limits certainty, but AWS IAM role listing is a non-mutating, informational operation.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs list_roles safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AWS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_roles, this is the rule to start with:

list_roles Allowed

list_roles is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "list_roles": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AWS, apply this rule, and every list_roles call is checked against it from then on.

FAQ

Questions about list_roles

What does the list_roles tool do? +

list_roles is a read tool on the AWS MCP server. It is categorised as a Read tool in the AWS MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on list_roles? +

Register the AWS MCP server in PolicyLayer and add a rule for list_roles: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches AWS. Nothing to install.

What risk level is list_roles? +

list_roles is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit list_roles? +

Yes. Add a rate_limit block to the list_roles rule in your PolicyLayer 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.

How do I block list_roles completely? +

Set action: deny in the PolicyLayer policy for list_roles. 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.

What MCP server provides list_roles? +

list_roles is provided by the AWS MCP server (@awslabs/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on AWS, and thousands of servers like it.

This server

All 300 AWS tools →

Across the catalogue

aiva_list_affiliates on AIVA MCP Server →list_circuits on 0gzk →list_agents on 0rca Dojo MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →