获取存储统计信息
AI agents call get_storage_stats to retrieve information from MinIO Storage MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves storage statistics and metrics from MinIO storage. It performs a read-only operation that gathers information about storage usage, capacity, or similar metrics. There is no indication of data modification, deletion, or financial impact. The function signature and description align with standard monitoring/telemetry retrieval, which is a classic Read category operation.
From the tool's definition Tool name 'get_storage_stats' and description '获取存储统计信息' (get storage statistics information) indicates retrieval of storage metrics without modifying or deleting data. No side effects implied.
Attacks that exploit this kind of access
获取存储统计信息. It is categorised as a Read tool in the MinIO Storage MCP MCP Server, which means it retrieves data without modifying state.
Register the MinIO Storage MCP server in PolicyLayer and add a rule for get_storage_stats: 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 Storage MCP. Nothing to install.
get_storage_stats 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 get_storage_stats 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 get_storage_stats. 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.
get_storage_stats is provided by the MinIO Storage MCP server (pickstar-2002/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 →