regex_split

What regex_split does on TinyFn

AI agents call regex_split to retrieve information from TinyFn without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Parameters from the server's own tool schema.

Why regex_split is rated Low

This tool performs a deterministic string operation that analyzes and transforms text into multiple parts without side effects. It reads input and returns computed results (split segments), fitting the Read category for data retrieval/transformation. The low severity reflects minimal blast radius even if misused—it cannot access external systems, delete data, execute code, or cause financial impact.

From the tool's definition Tool name 'regex_split' and description 'Split text by regex pattern' indicate a text processing operation that retrieves/queries data by partitioning input text according to a pattern. No modification, deletion, or execution of external operations occurs.

The rule that runs regex_split safely

PolicyLayer is an MCP gateway: it sits between your AI agents and TinyFn, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For regex_split, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "regex_split": {}
  }
}

Questions about regex_split