This record as markdown: /tools/io-tinyfn-tinyfn/regex-replace.md
What regex_replace does on TinyFn
AI agents use regex_replace to create or update resources in TinyFn, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your TinyFn environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to process |
flags | string | — | Flags: i=ignore case, m=multiline, s=dotall |
pattern | string | Yes | Regular expression pattern |
replacement | string | Yes | Replacement string |
Parameters from the server's own tool schema.
Why regex_replace is rated Medium
This tool creates or modifies data (text) in a reversible manner. While the modification could theoretically be undone or the original preserved, the primary action is transformation of input strings.
From the tool's definition Tool name 'regex_replace' and description 'Replace pattern matches in text' indicate the tool modifies text content based on pattern matching arguments.
Attacks that exploit this kind of access
The rule that runs regex_replace 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_replace, this is the rule to start with:
regex_replace stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect TinyFn, apply this rule, and every regex_replace call is checked against it from then on.
Questions about regex_replace
Replace pattern matches in text. It is categorised as a Write tool in the TinyFn MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
regex_replace accepts 4 parameters: text, flags, pattern, replacement. Required: text, pattern, replacement. The full parameter table on this page comes from the server's own tool schema.
Register the TinyFn MCP server in PolicyLayer and add a rule for regex_replace: 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 TinyFn. Nothing to install.
regex_replace is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the regex_replace 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 regex_replace. 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.
regex_replace is provided by the TinyFn MCP server (https://api.tinyfn.io/mcp/all/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on TinyFn, and thousands of servers like it.
This server
Across the catalogue