Find S3 buckets with public access enabled.
AI agents call find_public_s3_buckets to retrieve information from AWS FinOps 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 security/configuration data about S3 buckets (identifying those with public access) but does not modify, delete, or execute operations against them. It is a read-only discovery/audit tool.
From the tool's definition Tool name 'find_public_s3_buckets' and description 'Find S3 buckets with public access enabled' indicate a query/discovery operation that retrieves and lists information about S3 bucket configurations without modifying or deleting any resources.
Attacks that exploit this kind of access
Find S3 buckets with public access enabled. It is categorised as a Read tool in the AWS FinOps MCP Server MCP Server, which means it retrieves data without modifying state.
Register the AWS FinOps MCP Server MCP server in PolicyLayer and add a rule for find_public_s3_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 FinOps MCP Server. Nothing to install.
find_public_s3_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 find_public_s3_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 find_public_s3_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.
find_public_s3_buckets is provided by the AWS FinOps MCP Server MCP server (prashantgupta123/aws-pillar-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 →