Remove MCP servers from a tenant
AI agents call remove_servers_from_tenant to permanently remove resources in Pulsemcp Cms Admin — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Removing MCP servers from a tenant is a destructive operation: it severs the association between servers and a tenant, potentially affecting all users and services dependent on those servers. This action is not easily reversible and could have wide blast radius depending on how many users/services rely on the tenant's servers.
From the tool's definition 'remove_servers_from_tenant' — removing servers from a tenant is an irreversible dissociation action that could disrupt access and functionality for all users of that tenant
Attacks that exploit this kind of access
Remove MCP servers from a tenant. It is categorised as a Destructive tool in the Pulsemcp Cms Admin MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pulsemcp Cms Admin MCP server in PolicyLayer and add a rule for remove_servers_from_tenant: 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 Pulsemcp Cms Admin. Nothing to install.
remove_servers_from_tenant 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 remove_servers_from_tenant 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 remove_servers_from_tenant. 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.
remove_servers_from_tenant is provided by the Pulsemcp Cms Admin MCP server (pulsemcp-cms-admin-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 →