Language Detection Skill

Overview

Language Detector works by analyzing the text and comparing it to a database of languages and ai models. It uses advanced algorithms to detect the language of the text and returns the language code and the confidence level.

Live Test Language Detection Skill Skill →

The tool

Once your client is connected to the VerveKit server, this appears in its tool list as LanguageDetectionSkill. 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.

Tool call

{
  "name": "LanguageDetectionSkill",
  "arguments": {
    "text": "Guten Tag, wie geht es Ihnen?"
  }
}

You do not name the tool yourself; the model picks it. Asking about Guten Tag, wie geht es Ihnen? in the terms this skill covers is enough for it to reach for LanguageDetectionSkill on its own — naming it explicitly also works, and is the way to force the call.

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"
    }
  }
}

Per-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
`text`Required	string	The text to detect the language of

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.

Result

{
  "status": "ok",
  "error": null,
  "data": {
    "primaryLanguage": "spanish",
    "primaryCode": "es",
    "confidenceLevel": "medium",
    "detectedLanguages": [
      {
        "language": "spanish",
        "confidence": 0.38471794871794873,
        "code": "es"
      },
      {
        "language": "portuguese",
        "confidence": 0.2946153846153846,
        "code": "pt"
      },
      {
        "language": "danish",
        "confidence": 0.2464615384615384,
        "code": "da"
      }
    ]
  }
}

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
`primaryLanguage`	string	`spanish`	The most likely detected language
`primaryCode`	string	`es`	ISO 639-1 code of the primary language
`confidenceLevel`Premium	string	`medium`	Overall confidence level: high, medium, or low
`detectedLanguages`	array[3]		Every candidate language considered, ranked from most to least likely
`detectedLanguages.0.language`	string	`spanish`	The candidate language's full name
`detectedLanguages.0.confidence`	number	`0.38471794871794873`	How strongly the sample matched this language's trigram frequencies, from 0 to 1
`detectedLanguages.0.code`	string	`es`	ISO 639-1 code of this candidate language

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

Inbound Ticket Dispatch: When an international customer submits a support ticket, help desks inspect the text to route the ticket to native-speaking agents.
Voice Synthesizer Selection: To read articles aloud with correct accents, screen readers check the language code before choosing a matching text-to-speech voice model.
Search Stemmer Configuration: Tag document uploads with ISO language codes during ingest so search engines apply the correct grammatical stemming rules for each language.
Market Research Segmentation: Analytics teams group raw global survey responses by primary language before running regional sentiment and feedback models.

Other ways to use Language Detection Skill

Set up Language Detection 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.

Call it as a REST APIOne HTTPS endpoint and an x-api-key header, with SDKs for Node, Python and .NET.APIVerve →Reference →

Google Sheets or ExcelA =VERVE() formula fills a column — no script, no export, recalculates in place.VerveSheets →Reference →

Ground an agent on itA cited, machine-checkable fact your model can't produce on its own.VerveContext →Reference →