Overview
A random data API and random number generator API in one: pick a type and get JSON test data back. There are fourteen types: number, dice, coin, boolean, string, uuid, guid, color, phone, name, email, username, address and date. Numbers, dice, coins, booleans and strings come from a cryptographically secure generator, with min, max, decimals and unique (no repeats) for numbers, sides for dice, and length and charset for strings. Names, emails, usernames, phone numbers, addresses and dates are realistic fake values for seeding test databases and mock APIs; they don't belong to real people. The Free plan returns one value per call; paid plans return up to 100 at a time and can attach an AI-generated face to each name.
Live Test Random Data Skill Skill →
The tool
Once your client is connected to the VerveKit server, this appears in its tool list as RandomDataSkill. It is read-only and open-world — it fetches and never mutates anything on your side — so most clients call it without asking you to confirm.
{
"name": "RandomDataSkill",
"arguments": {}
}Connecting
One server URL covers every skill in the catalog, including this one. Authorization is OAuth: the client opens a browser once, and there is no key to paste into a config file.
{
"mcpServers": {
"vervekit": {
"url": "https://api.vervekit.com/v1/mcp"
}
}
}https://api.vervekit.com/v1/mcpPer-client setup — Claude, Cursor, VS Code, ChatGPT — is on the MCP setup page.
Arguments
These are the properties on the tool's inputSchema, so a well-behaved client validates them before the call is made. Premium arguments are accepted on every plan but only take effect on plans that include them.
| Argument | Type | Description |
|---|---|---|
typeOptional | string | The type of random data to generatenumberdicephonedatecoinuuidguidcolor+6default number |
countOptionalPremium | integer | The number of random data to generate (1 to 100) default 1 · range 1–100 |
includeAvatarOptionalPremium | boolean | Include an AI-generated face avatar (only applies when type=name) |
minOptional | number | Smallest number to draw, inclusive (type=number). Defaults to 0 |
maxOptional | number | Largest number to draw, inclusive (type=number). Defaults to 999999 default 999999 |
decimalsOptional | integer | Decimal places for type=number (0 to 10); 0 draws whole numbers range 0–10 |
uniqueOptional | boolean | Draw without repeats (type=number with whole numbers, or type=dice) |
sidesOptional | integer | Number of sides on each die for type=dice (2 to 1000) default 6 · range 2–1000 |
lengthOptional | integer | Length of each value for type=string (1 to 256) default 16 · range 1–256 |
charsetOptional | string | Characters for type=stringalphanumericalphanumerichexlowercaseuppercasedefault alphanumeric |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client reads fields without parsing prose. status is "ok" and error is null on success; a null field means the value was not available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"type": "phone",
"count": 10,
"data": [
"967-950-4587",
"792-611-7468 x1293",
"(933) 311-9829",
"389.357.7403 x793",
"1-621-490-6394",
"1-699-562-6833 x8558",
"875.226.1530 x641",
"744-991-0150 x1974",
"1-393-784-0533 x15199",
"954-876-6958 x0398"
]
}
}
Response fields
Paths are relative to data. Premium fields are absent rather than zeroed on plans that do not include them, so check for presence instead of comparing to 0.
| Field | Type | Example | Description |
|---|---|---|---|
type | string | phone | The kind of random data generated (e.g. phone, name, email) |
count | number | 10 | Number of random values generated |
data | array | ["967-950-4587","792-611-7468 x1293","(933) 311-9829"] | The generated random values; item shape depends on the requested type |
Failure modes
Errors come back as tool errors carrying a sentence the model can act on, not a bare status code. Error handling covers the full list.
| Status | What it means |
|---|---|
400 / 422 | The arguments did not validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Blocked by a key restriction or an IP allow-list. Never a bad identity. |
404 | This skill is not part of VerveKit. Check the catalog. |
429 | Out of credits, or a brief rate limit. The message tells them apart. |
A call costs 2 credits each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Database Seeding
- Populate staging tables with synthetic names, addresses, and phone numbers before running integration tests against newly deployed schemas.
- UI Prototype Mocking
- Front-end developers render placeholder user profiles with generated usernames, emails, and color names while building interface layouts.
- Unique Key Generation
- When verifying record deduplication pipelines, QA engineers inject generated UUIDs and timestamps into intake streams.
- Game Mechanics Simulation
- To test random drop rates and turn orders, game creators draw coin flips and dice rolls directly into prototype loops.
Other ways to use Random Data Skill
Set up Random Data Skill on VerveKit, or reach the same source a different way. Your VerveKit account and credits work on all of them — one key, one balance.
Related
More in Data Generation: