List all S3 buckets in the AWS account
AI agents call s3_list_buckets to retrieve information from AWS S3 MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about S3 buckets without creating, modifying, or deleting any resources. It is a read-only operation. Severity is medium rather than low because listing all buckets in an AWS account could expose organizational structure and bucket inventory to an AI agent, which could inform reconnaissance for further attacks if misused, but the tool itself performs no destructive or…
From the tool's definition Tool name is 's3_list_buckets' and description states 'List all S3 buckets in the AWS account' — a pure retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
List all S3 buckets in the AWS account. It is categorised as a Read tool in the AWS S3 MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS S3 MCP Server MCP server in PolicyLayer and add a rule for s3_list_buckets: 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 S3 MCP Server. Nothing to install.
s3_list_buckets 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 s3_list_buckets 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.
Set action: deny in the PolicyLayer policy for s3_list_buckets. 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.
s3_list_buckets is provided by the AWS S3 MCP Server MCP server (khuynh22/aws-s3-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →