Password Generator Skill
The tool
Let your agent create strong passwords. Call it as an MCP tool to generate one or many passwords at a chosen length and complexity.
Once your client is connected to the VerveKit MCP server, this appears in its tool list as PasswordGeneratorSkill. It is read-only and open-world: it fetches, it never mutates anything on your side, so most clients will call it without asking you to confirm.
{
"name": "PasswordGeneratorSkill",
"arguments": {
"count": "10",
"length": "12",
"complexity": "strong"
}
}What that looks like in a conversation
You don't name the tool — the model picks it. Asking about 10 in the terms this source covers is enough for it to reach for PasswordGeneratorSkill on its own.
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 Desktop, 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.
| Argument | Type | Example | Description |
|---|---|---|---|
countRequired | integer | 10 | The number of passwords to generate |
lengthRequired | integer | 12 | The length of the password to generate |
complexityRequired | string | strong | The complexity of the password. Only applies when type is random One of: simple, medium, strong, maximum. |
type | string | random | The kind of password to generate. random uses the complexity preset, pronounceable builds readable syllables, passphrase joins dictionary words, and custom honours the include/exclude switches below One of: random, pronounceable, passphrase, custom. |
includeNumbers | boolean | true | Include digits. Applies to custom and pronounceable, and to random at simple complexity |
includeSymbols | boolean | true | Include punctuation symbols. Applies to custom, and to random at medium complexity |
includeUppercase | boolean | true | Include uppercase letters. Applies to custom, and to random at simple complexity |
includeLowercase | boolean | true | Include lowercase letters in a custom password. Set false to build from the other character sets only |
excludeSimilar | boolean | true | Exclude characters that are easy to confuse when read aloud or typed (i, l, 1, L, o, 0, O) |
excludeAmbiguous | boolean | true | Exclude brackets, slashes, quotes and other characters that need escaping in shells and config files |
mixedCase | boolean | true | Randomly capitalise letters in a pronounceable password |
strict | boolean | true | Guarantee at least one character from every enabled set rather than leaving it to chance |
wordCount | integer | 4 | How many words a passphrase contains. Only applies when type is passphrase |
separator | string | - | The character placed between passphrase words. Only applies when type is passphrase |
capitalize | boolean | true | Capitalise each word of a passphrase. Only applies when type is passphrase |
analyzePremium | boolean | true | Return a strength analysis alongside each password |
What the model gets back
The result carries a structuredContent object matching the tool's declared outputSchema, so a client can read fields without parsing prose. status is "ok" on success and error is null; a null field means the value wasn't available for that input, not that the call failed.
{
"status": "ok",
"error": null,
"data": {
"passwords": [
{
"password": "aOwqDh0ZK*P;!M|%oiFYJ!IK%TMXQO",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{
"password": "Wo:)*V2nMakoVI78[fKu|QDI.E45p|",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{
"password": "%XqlsK2qN.9>*&jk6gYIG.[aE,hiRc",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{
"password": "WQNY0{R~(G99uc&i62Mve).n<|xt=F",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{
"password": "2$m-&z9!5$c3QlxQP{h#@0x~'M/h]T",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{
"password": "y]e_H)/z2yzbr{4C&hHOb[Q:#/$Hml",
"length": 30,
"metadata": {
"type": "random",
"complexity": "strong"
},
"analysis": null
},
{Fields
| Field | Type | Example | Description |
|---|---|---|---|
passwords | array[10] | list of rows | Array of generated password objects with details |
passwords.0.password | string | aOwqDh0ZK*P;!M|%oiFYJ!IK%TMXQO | |
passwords.0.length | number | 30 | |
passwords.0.metadata | object | {…} | |
passwords.0.metadata.type | string | random | |
passwords.0.metadata.complexity | string | strong | |
passwords.0.analysis | object | null | |
count | number | 10 | Total count of passwords generated |
Failure modes
Errors come back as tool errors with a sentence the model can act on, not a bare status code.
| Status | What it means |
|---|---|
400 / 422 | The arguments didn't validate. The message names the offending one. |
401 | The OAuth session is invalid or expired — reconnect the server. |
403 | Out of credits. Not a bad key — the month's allowance is spent. |
404 | This skill isn't part of VerveKit. Check the catalog. |
429 | Brief rate limit. Retrying after a moment succeeds. |
Other ways to use Password Generator Skill
Set up Password Generator 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.
Frequently asked questions
Do I have to tell the agent to use PasswordGeneratorSkill?
No. The tool's name and description are in the model's context once the server is connected, so it selects the tool when the question calls for it. Naming it explicitly works too and is useful when you want to force the call.
Does connecting the server expose every tool at once?
Yes — one connection lists the whole VerveKit catalog. Clients with a tool budget can usually filter the list; the credit cost is per call, so an unused tool costs nothing.
What does a call cost?
1 credit each time the tool actually runs. A model that reasons about the tool without calling it costs nothing.
Is there a REST version of this?
Yes — the same source is available as a plain HTTPS endpoint on APIVerve, linked above. Same data, same credits, same account.