AI agents call random_phone to retrieve information from TinyFn without modifying anything — 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 phone numbers to generate |
locale | object | — | Locale for phone format (e.g., en_US, en_GB, de_DE, ja_JP) |
Parameters from the server's own tool schema.
This tool produces synthetic data (random phone numbers) deterministically without side effects, system queries, or external state changes. It is a data generation utility that falls under the Read category as a data-producing function with no reversible or irreversible modifications to real systems. Severity is low because misuse would only generate harmless synthetic values with no operational impact.
From the tool's definition Tool generates random phone numbers using Faker library; described as 'Generate random phone number(s)' with no indication of data retrieval from actual systems, modification, execution, or destructive operations.
Attacks that exploit this kind of access
Generate random phone number(s) using Faker with locale-appropriate formats. It is categorised as a Read tool in the TinyFn MCP Server, which means it retrieves data without modifying state.
random_phone accepts 2 parameters: count, locale. 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_phone: 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_phone 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_phone 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_phone. 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_phone 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.
random_phone is one line of TinyFn'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 →