AI agents call find to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves filesystem metadata (file paths, names, extensions) without modifying, deleting, or executing anything. It is analogous to a filesystem search or list operation. The only risk is information disclosure if sensitive file paths exist, but that is a low-severity read concern. Confidence is high because the description is clear and explicit about the read-only nature.
From the tool's definition Tool description states it "Finds files and directories" and "Returns file paths, names, and extensions." The verb "find" combined with "returns" data indicates a read-only query operation with no side effects.
Attacks that exploit this kind of access
Finds files and directories using fd with structured output. Returns file paths, names, and extensions. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for find: 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 Python. Nothing to install.
find 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 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. 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 is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
find is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →