format
AI agents call format to permanently remove resources in Windows Operations MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
In Windows context, 'format' almost certainly refers to formatting a disk/volume (e.g., FORMAT C:), which is an irreversible destructive operation that erases all data on a storage device. Given the server's focus on Windows system management and administration, this interpretation is highly probable. The blast radius is critical — misuse could wipe entire drives.
From the tool's definition Tool name 'format' on a Windows system management server with CMD/PowerShell execution capabilities. The description is empty and uninformative.
Attacks that exploit this kind of access
format. It is categorised as a Destructive tool in the Windows Operations MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Windows Operations MCP server in PolicyLayer and add a rule for format: 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 Windows Operations MCP. Nothing to install.
format 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 format 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 format. 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.
format is provided by the Windows Operations MCP server (sandraschi/windows-operations-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 →