AI agents call account_status 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 account metadata (status, billing, subscription info, etc.) with no side effects. It is a passive read operation analogous to a GET request. Even if the account info includes sensitive data, the tool itself performs no destructive, financial, or executable actions—it only queries and returns existing information.
From the tool's definition Tool name 'account_status' and description 'Return ChatGPT account info' indicate a query operation that retrieves account information without modifying or executing anything.
Attacks that exploit this kind of access
Return ChatGPT account info. 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 account_status: 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.
account_status 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 account_status 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 account_status. 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.
account_status 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 →