AI agents call find_files to retrieve information from MCPHub without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search for or list files on the system, which is a read-only operation. Without evidence of modification, deletion, or execution capabilities, this falls into the Read category. Severity is low because file enumeration alone presents minimal risk; dangerous only if an agent combines results with other destructive tools.
From the tool's definition Tool name 'find_files' suggests a file search/query operation with no side effects. Description is empty, but the name strongly indicates retrieval of file information rather than modification or deletion.
Attacks that exploit this kind of access
find_files. It is categorised as a Read tool in the MCPHub MCP Server, which means it retrieves data without modifying state.
Register the MCPHub MCP server in PolicyLayer and add a rule for find_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 MCPHub. Nothing to install.
find_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 find_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 find_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.
find_files is provided by the MCPHub MCP server (jayden-dong/mcphub). 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 →