Close an active SSH session.
AI agents invoke ssh_disconnect to trigger actions in Claude Ssh. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Disconnecting an SSH session terminates an active network connection and any running processes tied to that session. While not destructive to data, it is an operational action with real side effects (terminating remote processes, interrupting ongoing work) that cannot be trivially undone. It falls under Execute as it triggers an external operation affecting the SSH connection state.
From the tool's definition Close an active SSH session
Attacks that exploit this kind of access
Close an active SSH session. It is categorised as a Execute tool in the Claude Ssh MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Ssh MCP server in PolicyLayer and add a rule for ssh_disconnect: 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_disconnect is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the ssh_disconnect 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_disconnect. 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_disconnect 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 →