uninstall_mcp_server
AI agents call uninstall_mcp_server to permanently remove resources in MCP Proxy — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Uninstalling an MCP server removes it from the system state irreversibly. While not as immediately critical as data deletion, this is a destructive action that cannot be undone by the tool itself (reinstallation is a separate operation). The empty description reduces confidence slightly, but the name strongly indicates a destructive capability.
From the tool's definition Tool name is 'uninstall_mcp_server' with empty description. 'Uninstall' indicates removal/deletion of installed software packages, which is irreversible without reinstallation.
Attacks that exploit this kind of access
uninstall_mcp_server. It is categorised as a Destructive tool in the MCP Proxy MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the MCP Proxy MCP server in PolicyLayer and add a rule for uninstall_mcp_server: 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 Proxy. Nothing to install.
uninstall_mcp_server 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 uninstall_mcp_server 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 uninstall_mcp_server. 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.
uninstall_mcp_server is provided by the MCP Proxy MCP server (lizthedeveloper/mcp_proxy). 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 →