Delete a provider for a tenant
AI agents call delete_tenant_provider to permanently remove resources in UseGrant MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes a provider association from a tenant, which cannot be undone and will disrupt access management. The deletion of authentication/authorization infrastructure represents a destructive action with high blast radius if misused by an AI agent—it could revoke legitimate access for multiple clients or users relying on that provider.
From the tool's definition Tool name explicitly states 'delete_tenant_provider' and description confirms 'Delete a provider for a tenant'. The 'delete' operation is irreversible and removes access control infrastructure.
Attacks that exploit this kind of access
Delete a provider for a tenant. It is categorised as a Destructive tool in the UseGrant MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the UseGrant MCP Server MCP server in PolicyLayer and add a rule for delete_tenant_provider: 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 UseGrant MCP Server. Nothing to install.
delete_tenant_provider 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 delete_tenant_provider 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 delete_tenant_provider. 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.
delete_tenant_provider is provided by the UseGrant MCP Server MCP server (usegranthq/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 →