批量下载文件
AI agents call download_files 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 retrieves/queries files from storage with no side effects. It does not create, modify, delete, execute code, or commit financial transactions. The batch download capability does not change its fundamental Read classification. Severity is low because downloading files poses minimal risk—the worst case is exposure of data the user already has permission to access.
From the tool's definition Tool name 'download_files' and description '批量下载文件' (batch download files) indicate retrieval of existing data from MinIO object storage without modification, deletion, or execution of code.
Attacks that exploit this kind of access
批量下载文件. 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 download_files: 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.
download_files 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 download_files 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 download_files. 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.
download_files 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 →