Remove an owner-scoped OAuth client by owner and slug. Existing connections are not cascaded.
AI agents call oauth.clients.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 an OAuth client configuration. OAuth clients are critical authentication artifacts—removing one irreversibly revokes access tokens and credentials. While the description notes that existing connections are not cascaded (a partial mitigation), the core operation is destructive deletion. An AI agent misusing this could disable legitimate OAuth integrations or authentication flows.
From the tool's definition 'Remove' an OAuth client by owner and slug; the operation 'cannot be undone' once deleted, even though 'Existing connections are not cascaded'. This is an irreversible deletion of authentication credentials.
Documented attack patterns abuse exactly the kind of access oauth.clients.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 oauth.clients.remove:
{
"version": "1",
"default": "deny",
"hide": [
"oauth.clients.remove"
]
}oauth.clients.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 an owner-scoped OAuth client by owner and slug. Existing connections are not cascaded. 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 oauth.clients.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.
oauth.clients.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 oauth.clients.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 oauth.clients.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.
oauth.clients.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.