Disconnect from the remote machine.
AI agents invoke ssh_disconnect to trigger actions in SSH Read-Only MCP Server. 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 is not a simple read or write; it triggers an external operation (tearing down the connection) that affects ongoing remote access. While the server is described as read-only for command execution, disconnecting is an operational action with real side effects (e.g., interrupting running processes or audit sessions).
From the tool's definition 'Disconnect from the remote machine' — terminates an active SSH connection, an external operational side-effect that cannot be trivially undone without reconnecting
Attacks that exploit this kind of access
Disconnect from the remote machine. It is categorised as a Execute tool in the SSH Read-Only MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SSH Read-Only MCP Server 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 SSH Read-Only MCP Server. 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 SSH Read-Only MCP Server MCP server (kunwarmahen/ssh-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 →