AI agents call list_apps 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 queries and retrieves a list of connected applications without modifying, executing, or deleting anything. It has minimal security impact as it only exposes metadata about integrations already authorized by the user. The lack of any write, execute, or destructive capability places it firmly in the Read category with low severity.
From the tool's definition Tool description states 'Return ChatGPT connected apps/connectors' — a retrieval operation with no modification or side effects. The verb 'Return' and the informational nature (listing existing connections) confirm this is a read-only query.
Attacks that exploit this kind of access
Return ChatGPT connected apps/connectors. Names unresolvable — IDs with type classification returned. 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 list_apps: 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.
list_apps 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_apps 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_apps. 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_apps 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 →