Remove a saved server from servers.json and disconnect if currently active.
AI agents call ssh_remove_server to permanently remove resources in Claude Ssh — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes server configuration entries from a persistent store. While the data itself is not highly sensitive, the action is irreversible and represents loss of state. An AI agent mistakenly removing critical server configurations could disrupt infrastructure management workflows.
From the tool's definition The tool 'ssh_remove_server' removes a saved server from servers.json and disconnects if currently active. This is an irreversible deletion of configuration data ('Remove a saved server from servers.json').
Attacks that exploit this kind of access
Remove a saved server from servers.json and disconnect if currently active. It is categorised as a Destructive tool in the Claude Ssh MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Claude Ssh MCP server in PolicyLayer and add a rule for ssh_remove_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 Claude Ssh. Nothing to install.
ssh_remove_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 ssh_remove_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 ssh_remove_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.
ssh_remove_server is provided by the Claude Ssh MCP server (marabank/mcp-ssh-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 →