revoke
AI agents call revoke 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.
The description is empty, which forces reliance on the tool name alone. 'Revoke' in a Windows administration context most commonly means removing permissions, revoking certificates, or invalidating credentials/tokens. These actions are typically irreversible (e.g., revoking a certificate cannot be undone; access must be re-granted explicitly).
From the tool's definition Tool name 'revoke' with empty description. In Windows system management context, 'revoke' typically refers to revoking permissions, certificates, tokens, or access rights — actions that are generally irreversible or require significant effort to undo.
Attacks that exploit this kind of access
revoke. 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 revoke: 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.
revoke 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 revoke 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 revoke. 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.
revoke 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 →