Overview
Each flip draws one pseudo-random number and calls it Heads when the value is below 0.5 and Tails otherwise, so both sides have the same chance and no flip depends on the one before it. `flips` holds the results in the order they were generated, `total_flips` is how many were made, and `heads_count` and `tails_count` always add up to it. `first_flip` and `last_flip` are the first and last entries of that array.
The `flips` parameter defaults to 1 and accepts up to 10,000. Larger values are capped at 10,000, and values below 1 are treated as 1. The array grows with the count, so a 10,000-flip response carries 10,000 strings.
`heads_percentage` and `tails_percentage` are the counts divided by `total_flips`, times 100, rounded to two decimals: 30 means 30%, not 0.30. `longest_streak` scans the sequence for the longest run of identical results; `length` is the run size and `type` is the side. When two runs tie, the earlier one is reported, and a single flip has a streak of 1.
`is_fair` is true when the heads percentage is strictly within 10 percentage points of 50. It is a fixed tolerance band, not a statistical test, so small batches often read false: three heads in ten flips is 30% and returns false although nothing is wrong with the generator. Judge fairness on large batches.
On the Free plan the `flips` parameter is removed, so every call makes exactly one flip, and the percentage fields and `is_fair` are null.
Live Test Coin Flip Skill Skill →
The tool
Once your client is connected to the VerveKit server, this appears in its tool list as CoinFlipSkill. 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": "CoinFlipSkill",
"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 |
|---|---|---|
flipsOptionalPremium | integer | Number of coins to flip default 1 · range 1–10000 |
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": {
"total_flips": 10,
"flips": [
"Tails",
"Heads",
"Heads",
"Tails",
"Tails",
"Heads",
"Tails",
"Tails",
"Tails",
"Tails"
],
"heads_count": 3,
"tails_count": 7,
"heads_percentage": 30,
"tails_percentage": 70,
"longest_streak": {
"length": 4,
"type": "Tails"
},
"first_flip": "Tails",
"last_flip": "Tails",
"is_fair": false
}
}
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 |
|---|---|---|---|
total_flips | number | 10 | Total number of coin flips performed in simulation |
flips | array | ["Tails","Heads","Heads"] | Array of individual flip results as Heads or Tails |
heads_count | number | 3 | Total count of heads outcomes from all flips |
tails_count | number | 7 | Total count of tails outcomes from all flips |
heads_percentagePremium | number | 30 | Percentage of heads outcomes as decimal |
tails_percentagePremium | number | 70 | Percentage of tails outcomes as decimal |
longest_streak | object | {…} | The longest run of the same result anywhere in this set of flips |
longest_streak.lengthPremium | number | 4 | How many flips long that run was |
longest_streak.typePremium | string | Tails | Which result the run was made of, Heads or Tails |
first_flip | string | Tails | Result of the first coin flip performed |
last_flip | string | Tails | Result of the last coin flip performed |
is_fairPremium | boolean | false | Statistical indicator of fair coin flip distribution |
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 1 credit each time the tool actually runs; a model that reasons about the tool without calling it costs nothing.
Use cases
- Decision Making
- Make random decisions and choices using fair coin flip probability
- Gaming
- Implement coin flip mechanics for games, sports, and random selection features
- Probability Teaching
- Demonstrate probability concepts and random distributions in education
- Simulations
- Run probability experiments and test statistical concepts with multiple flips
Other ways to use Coin Flip Skill
Set up Coin Flip 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 Games: