Disconnect a touch session and clean up the remote daemon.
AI agents invoke touch_disconnect to trigger actions in Mcp Remotetouch. 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.
This tool terminates an active SSH/touch session and cleans up a remote daemon process. While it involves teardown of a running process (execute category), it is not purely destructive in the sense of deleting user data, but it does trigger external operations on a remote machine.
From the tool's definition 'Disconnect a touch session and clean up the remote daemon'
Attacks that exploit this kind of access
Disconnect a touch session and clean up the remote daemon. It is categorised as a Execute tool in the Mcp Remotetouch MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Remotetouch MCP server in PolicyLayer and add a rule for touch_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 Mcp Remotetouch. Nothing to install.
touch_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 touch_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 touch_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.
touch_disconnect is provided by the Mcp Remotetouch MCP server (signal-slot/mcp-remotetouch). 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 →