Remove a saved connection and its produced tools by owner, integration, and connection name.
AI agents call connections.remove to permanently remove resources in Executor — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes a saved connection and its produced tools. The operation is irreversible—once removed, the connection configuration and all associated tools are gone. This cannot be undone or recovered without manual restoration. While it doesn't delete user data directly, removing a connection could disrupt dependent workflows and integrations.
From the tool's definition The tool description explicitly uses "Remove a saved connection" which indicates irreversible deletion of a saved connection and its associated tools. The word "remove" combined with "saved connection" indicates a destructive operation that cannot be undone.
Documented attack patterns abuse exactly the kind of access connections.remove gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Executor, and nothing reaches the server without passing your rules. This is the rule we recommend for connections.remove:
{
"version": "1",
"default": "deny",
"hide": [
"connections.remove"
]
}connections.remove disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove a saved connection and its produced tools by owner, integration, and connection name. It is categorised as a Destructive tool in the Executor MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Executor MCP server in PolicyLayer and add a rule for connections.remove: 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 Executor. Nothing to install.
connections.remove 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 connections.remove 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 connections.remove. 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.
connections.remove is provided by the Executor MCP server (rhyssullivan/executor). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 29 Executor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
29 Executor tools catalogued and risk-classified — across an index of 42,500+ MCP servers.