Archive a Codex Cloud chat (move it out of the active list).
AI agents use archive_chat to create or update resources in Codex Chats — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Codex Chats environment.
This tool modifies data state (moving a chat to archived status) but does not irreversibly delete or destroy data, and does not execute code or handle financial transactions. The operation is reversible—archived chats can be recovered or un-archived. This qualifies as Write rather than Destructive.
From the tool's definition Archive a Codex Cloud chat (move it out of the active list). The tool modifies the state of a chat by relocating it to an archived state, which is a reversible operation.
Attacks that exploit this kind of access
Archive a Codex Cloud chat (move it out of the active list). It is categorised as a Write tool in the Codex Chats MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Codex Chats MCP server in PolicyLayer and add a rule for archive_chat: 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 Chats. Nothing to install.
archive_chat is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the archive_chat 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 archive_chat. 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.
archive_chat is provided by the Codex Chats MCP server (shoyu-ramen/codex-chats-mcp). 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 →