Fetch the full payload for a regular ChatGPT conversation, including its message tree.
AI agents call get_conversation 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.
This tool retrieves and queries conversation data without altering, deleting, or executing any operations. It has no side effects beyond reading the message tree payload. The associated sibling tools (delete_*, archive_*) show destructive/write capabilities exist separately on this server, but this specific tool is purely informational.
From the tool's definition Tool description explicitly states 'Fetch the full payload' for a conversation, indicating data retrieval. The verb 'fetch' and the absence of any modification language (create, update, delete, modify) confirm this is a read-only operation.
Attacks that exploit this kind of access
Fetch the full payload for a regular ChatGPT conversation, including its message tree. 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 get_conversation: 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.
get_conversation 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 get_conversation 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 get_conversation. 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.
get_conversation 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 →