Delete an installed MCP server and its environment
AI agents call delete_mcp to permanently remove resources in MCP Secure Installer — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes an installed MCP server and its associated environment. Deletion is irreversible and cannot be undone without external intervention (e.g., restore from backup). The blast radius includes loss of server configuration, data, and dependencies.
From the tool's definition Tool name is 'delete_mcp' and description states 'Delete an installed MCP server and its environment' — the verb 'delete' and the scope (server + environment) indicate irreversible removal of data and system state.
Attacks that exploit this kind of access
Delete an installed MCP server and its environment. It is categorised as a Destructive tool in the MCP Secure Installer MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Secure Installer MCP server in PolicyLayer and add a rule for delete_mcp: 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 Secure Installer. Nothing to install.
delete_mcp 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_mcp 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_mcp. 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_mcp is provided by the MCP Secure Installer MCP server (mossaka/mcp-sinstaller). 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 →