List objects in a MinIO bucket
AI agents call minio_list_objects to retrieve information from MinIO 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 enumerates objects stored in a bucket. It is a read-only operation that queries existing data without creating, modifying, deleting, or executing anything. While information disclosure could be a concern depending on bucket contents and access controls, the tool itself performs no destructive or harmful action — an AI agent cannot cause damage by calling list operations.
From the tool's definition Tool name is 'minio_list_objects' and description states it 'List objects in a MinIO bucket' — a pure query/retrieval operation with no data modification, deletion, or side effects.
Attacks that exploit this kind of access
List objects in a MinIO bucket. It is categorised as a Read tool in the MinIO MCP Server MCP Server, which means it retrieves data without modifying state.
Register the MinIO MCP Server MCP server in PolicyLayer and add a rule for minio_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 MinIO MCP Server. Nothing to install.
minio_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 minio_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 minio_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.
minio_list_objects is provided by the MinIO MCP Server MCP server (raphaelren/minio-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 →