This record as markdown: /tools/io-tinyfn-tinyfn/random-choice.md
What random_choice does on TinyFn
AI agents call random_choice 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
count | integer | — | Number of choices to make |
items | string | Yes | Comma-separated items to choose from |
allow_duplicates | boolean | — | Allow same item to be chosen multiple times |
Parameters from the server's own tool schema.
Why random_choice is rated Low
This tool reads from a provided list and returns a random selection. It does not create, modify, delete, or execute external operations. The randomness is deterministic (as noted in server description of '500+ deterministic tools'), making it a pure query function with no side effects or risk of unintended consequences.
From the tool's definition Tool description states 'Pick random item(s) from a list' — a read operation that retrieves and returns data without modification or side effects.
Attacks that exploit this kind of access
The rule that runs random_choice 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 random_choice, this is the rule to start with:
random_choice is read-only, so it stays allowed. 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 random_choice call is checked against it from then on.
Questions about random_choice
Pick random item(s) from a list. It is categorised as a Read tool in the TinyFn MCP Server, which means it retrieves data without modifying state.
random_choice accepts 3 parameters: count, items, allow_duplicates. Required: items. 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 random_choice: 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.
random_choice 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 random_choice 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 random_choice. 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.
random_choice 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