Cancel a running Codex task by killing its tmux session.
AI agents call codex_cancel to permanently remove resources in Codex — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing a tmux session is an irreversible action — the running task and its session state are destroyed. Any unsaved in-progress work within that session is permanently lost. This cannot be undone, placing it firmly in the Destructive category. Severity is high because it can terminate long-running autonomous coding tasks mid-execution, potentially leaving work in an inconsistent state.
From the tool's definition Cancel a running Codex task by killing its tmux session
Attacks that exploit this kind of access
Cancel a running Codex task by killing its tmux session. It is categorised as a Destructive tool in the Codex MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Codex MCP server in PolicyLayer and add a rule for codex_cancel: 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 Codex. Nothing to install.
codex_cancel 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 codex_cancel 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 codex_cancel. 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.
codex_cancel is provided by the Codex MCP server (shilong20/codexmcp). 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 →