AI agents call memory_list to retrieve information from Openai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves ChatGPT memory data in a read-only manner. While memories may contain sensitive information, the PII redaction and lack of any modification, deletion, or execution capability place this firmly in the Read category. Severity is low because the data returned is already redacted, limiting exposure of personally identifiable information.
From the tool's definition Tool name 'memory_list' and description 'Return all ChatGPT memories' indicate retrieval/query operation with no modification capability. PII redaction further confirms data retrieval intent without side effects.
Attacks that exploit this kind of access
Return all ChatGPT memories (PII redacted). It is categorised as a Read tool in the Openai MCP Server, which means it retrieves data without modifying state.
Register the Openai MCP server in PolicyLayer and add a rule for memory_list: 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 Openai. Nothing to install.
memory_list 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 memory_list 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 memory_list. 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.
memory_list is provided by the Openai MCP server (robotlearning123/gpt2agent). 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 →