Reset the conversation session with Codex. Clears history and stats. Use when starting a new topic.
AI agents call codex_reset to permanently remove resources in Codex Bridge — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool irreversibly clears conversation history and statistics. Once reset, prior session data (history and stats) cannot be recovered, making this a destructive operation. However, blast radius is limited to session/conversation data rather than production systems or user data, hence medium severity.
From the tool's definition Reset the conversation session with Codex. Clears history and stats.
Attacks that exploit this kind of access
Reset the conversation session with Codex. Clears history and stats. Use when starting a new topic. It is categorised as a Destructive tool in the Codex Bridge MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Codex Bridge MCP server in PolicyLayer and add a rule for codex_reset: 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 Bridge. Nothing to install.
codex_reset 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_reset 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_reset. 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_reset is provided by the Codex Bridge MCP server (ndcorder/claude-codex-team). 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 →