AI agents use memory_create_via_chat to create or update resources in Openai — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Openai environment.
The 'create' verb in the tool name strongly suggests writing or persisting data (likely conversation memory or state). Without description details, this appears to be a Write operation rather than Read (no query semantics) or Destructive (no 'delete'/'purge' language). Severity is medium because memory operations could track or persist unintended information, but lack of detail justifies moderate confidence (0.60).
From the tool's definition Tool name 'memory_create_via_chat' contains 'create', indicating irreversible data creation or persistence. No formal description provided to disambiguate scope or reversibility.
Attacks that exploit this kind of access
memory_create_via_chat. It is categorised as a Write tool in the Openai MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Openai MCP server in PolicyLayer and add a rule for memory_create_via_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 Openai. Nothing to install.
memory_create_via_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 memory_create_via_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 memory_create_via_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.
memory_create_via_chat 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 →