List files available for assistants
AI agents call list-files 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 tool retrieves or queries file metadata associated with assistants without creating, modifying, or deleting data. It is a read-only operation that falls clearly into the Read category. The severity is low because listing files poses minimal security risk—it does not execute code, modify data, or expose sensitive content beyond what the caller already has access to manage.
From the tool's definition Tool name 'list-files' and description 'List files available for assistants' indicate a query/retrieval operation with no side effects.
Attacks that exploit this kind of access
List files available for 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-files: 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-files 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-files 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-files. 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-files 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 →