AI agents use ssh_disconnect to create or update resources in Ssh Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ssh Agent environment.
Disconnecting an SSH session is a write operation that modifies system state reversibly. While it terminates a connection, it does not destroy persistent data or execute arbitrary code. The severity is medium because disconnecting legitimate sessions could disrupt workflows, but the impact is contained to connection state and easily recoverable.
From the tool's definition Tool name 'ssh_disconnect' and description indicating closure of SSH connections. The tool modifies connection state by terminating an established session, which is a reversible state change (reconnection is possible).
Attacks that exploit this kind of access
断开SSH连接. It is categorised as a Write tool in the Ssh Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ssh Agent 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 Agent. Nothing to install.
ssh_disconnect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
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 Agent MCP server (zhijun/ssh-mcp). 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 →