List objects in an S3 bucket with optional prefix filtering
AI agents call s3_list_objects 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 retrieves and lists S3 objects without altering, deleting, or executing any operations on them. It is a read-only operation with minimal blast radius—at most, an AI agent could enumerate bucket contents to discover sensitive object names, but cannot access, modify, or delete them without other tools. Confidence is high because the operation is clearly read-only.
From the tool's definition Tool name 's3_list_objects' and description 'List objects in an S3 bucket with optional prefix filtering' indicate a query/enumeration operation with no modification or deletion of data.
Attacks that exploit this kind of access
List objects in an S3 bucket with optional prefix filtering. 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_objects: 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_objects 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_objects 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_objects. 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_objects 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 →