List regular ChatGPT conversations (the 'Recents' list, not Codex tasks).
AI agents call list_conversations to retrieve information from Codex Chats without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and lists existing conversation metadata without side effects. No data is created, modified, deleted, or overwritten. This is a straightforward read operation querying the 'Recents' list of conversations. Low severity because the blast radius of misuse is minimal—an AI agent cannot cause data loss, financial harm, or irreversible changes by listing conversations.
From the tool's definition Tool name 'list_conversations' and description 'List regular ChatGPT conversations' indicate a retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
List regular ChatGPT conversations (the 'Recents' list, not Codex tasks). It is categorised as a Read tool in the Codex Chats MCP Server, which means it retrieves data without modifying state.
Register the Codex Chats MCP server in PolicyLayer and add a rule for list_conversations: 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.
list_conversations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_conversations 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 list_conversations. 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.
list_conversations 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 →