AI agents call list_objects 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.
This tool retrieves and enumerates objects from an S3-compatible storage bucket without modifying, deleting, or executing any operations. It is a pure read operation. Severity is low because listing bucket contents, while potentially revealing sensitive object names, does not directly expose object data, modify resources, or trigger external actions.
From the tool's definition Tool name 'list_objects' and description 'List objects in a bucket' clearly indicate a retrieval operation with no side effects. The mention of optional filtering by key prefix and delimiter parameter confirms it is a query operation.
Attacks that exploit this kind of access
List objects in a bucket (optionally under a key prefix). Pass delimiter='/'. 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 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 Rustfs. Nothing to install.
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 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 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.
list_objects 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 →