AI agents call bucket_usage to retrieve information from Rustfs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
bucket_usage reads and computes summary metadata from an S3 bucket. It queries existing state without creating, modifying, deleting, or executing operations. The blast radius is minimal: an agent querying bucket usage cannot alter data, trigger external operations, or cause financial harm. Low severity due to read-only nature and limited scope.
From the tool's definition Tool retrieves aggregate statistics ('Total object count + byte size') by paginating through bucket contents without modification. No side effects indicated in the name or description.
Attacks that exploit this kind of access
Total object count + byte size of a bucket (paginates the whole bucket). It is categorised as a Read tool in the Rustfs MCP Server, which means it retrieves data without modifying state.
Register the Rustfs MCP server in PolicyLayer and add a rule for bucket_usage: 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 Rustfs. Nothing to install.
bucket_usage 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 bucket_usage 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 bucket_usage. 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.
bucket_usage is provided by the Rustfs MCP server (stackblaze/rustfs-mcp). 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 →