Permanently disconnect (delete) a channel from the workspace. Destructive: cancels all pending posts on this channel and removes it. The caller MUST set confirm=true to proceed — this prevents an LLM from removing a channel by accident. Reconnecting requires the user to re-authorize the platform ...
AI agents call disconnect_channel to permanently remove resources in Viraly MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs an irreversible deletion of a workspace channel and its associated data (pending posts). The destructive nature is confirmed by explicit language in the description, the requirement for explicit confirmation (confirm=true), and the fact that recovery requires external re-authorization.
From the tool's definition Tool description explicitly states 'Permanently disconnect (delete) a channel from the workspace' and 'Destructive: cancels all pending posts on this channel and removes it.' The action irreversibly deletes a channel and cancels associated posts, which cannot…
Attacks that exploit this kind of access
Permanently disconnect (delete) a channel from the workspace. Destructive: cancels all pending posts on this channel and removes it. The caller MUST set confirm=true to proceed — this prevents an LLM from removing a channel by accident. Reconnecting requires the user to re-authorize the platform via the Viraly SPA. It is categorised as a Destructive tool in the Viraly MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Viraly MCP Server MCP server in PolicyLayer and add a rule for disconnect_channel: 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 Viraly MCP Server. Nothing to install.
disconnect_channel 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 disconnect_channel 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 disconnect_channel. 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.
disconnect_channel is provided by the Viraly MCP Server MCP server (viraly-io/viraly-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 →