Use an AI agent specialized in searching through files and documents to find relevant information.
AI agents call file_search_agent to retrieve information from OpenAI Agents MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
File search is fundamentally a Read operation as it queries and retrieves information without side effects. Severity is medium rather than low because: (1) an AI agent could be directed to search for and exfiltrate sensitive documents, credentials, or PII; (2) the agent operates on an AI system with potential access to user files; (3) context from sibling tools (computer_action_agent, web_search_agent) suggests…
From the tool's definition Tool description states it "searching through files and documents to find relevant information" - a retrieval operation with no modification or destructive capability.
Documented attack patterns abuse exactly the kind of access file_search_agent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenAI Agents MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for file_search_agent:
{
"version": "1",
"default": "deny",
"tools": {
"file_search_agent": {}
}
}file_search_agent is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Use an AI agent specialized in searching through files and documents to find relevant information. It is categorised as a Read tool in the OpenAI Agents MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenAI Agents MCP Server MCP server in PolicyLayer and add a rule for file_search_agent: 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 Agents MCP Server. Nothing to install.
file_search_agent 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 file_search_agent 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 file_search_agent. 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.
file_search_agent is provided by the OpenAI Agents MCP Server MCP server (lroolle/openai-agents-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenAI Agents MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 OpenAI Agents MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.