Interact with cloud storage services - upload, download, list, delete files
AI agents call cloud_storage to permanently remove resources in MCP Workspace Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Because the tool bundles delete alongside upload/download/list, and deletion of cloud storage files can be irreversible, the most severe applicable category is Destructive. An AI agent misusing this tool could permanently remove files from cloud storage, warranting high severity.
From the tool's definition 'upload, download, list, delete files' — the tool explicitly includes delete operations on cloud storage
Attacks that exploit this kind of access
Interact with cloud storage services - upload, download, list, delete files. It is categorised as a Destructive tool in the MCP Workspace Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Workspace Server MCP server in PolicyLayer and add a rule for cloud_storage: 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 MCP Workspace Server. Nothing to install.
cloud_storage is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the cloud_storage 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 cloud_storage. 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.
cloud_storage is provided by the MCP Workspace Server MCP server (shayyeffet/ultimate_mcp_server). 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 →