List OpenAI assistants
AI agents call list-assistants to retrieve information from OpenAI Assistant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a query/retrieval operation (list) that returns information about existing assistants. It performs no modifications, does not execute code, and has no irreversible effects. The blast radius is minimal—an agent listing assistants could at worst gain knowledge of available assistants but cannot create, modify, or delete them with this tool alone.
From the tool's definition Tool name 'list-assistants' and description 'List OpenAI assistants' indicate a read-only operation that retrieves data without modification or side effects.
Attacks that exploit this kind of access
List OpenAI assistants. It is categorised as a Read tool in the OpenAI Assistant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenAI Assistant MCP Server MCP server in PolicyLayer and add a rule for list-assistants: 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 Assistant MCP Server. Nothing to install.
list-assistants 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-assistants 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-assistants. 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-assistants is provided by the OpenAI Assistant MCP Server MCP server (snilld-ai/openai-assistant-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 →