MCP tool reference · #325 of 563 by publishers
detect_language
Exposed by 11 servers from 10 publishers, read from the live servers by the Serverdex check; most of them sit in AI & Agents; 90.9% of them take a text parameter; the most-starred is Text Analysis & Cleanup Tools (Tanod) (1 stars).
detect_language(text: string, …)Parameters
share = % of the 11 servers whose schema has it · required = % of those that mark it required| Parameter | Type | Share | Required | Usual description |
|---|---|---|---|---|
| text | string | 90.9% | 100% | The text (at most 20,000 characters). |
| top_k | integer | 18.2% | 0% | Number of top language predictions to return |
| idempotency_key | string | 9.1% | 0% | Optional per-job key; relevant when COST_DETECT_LANGUAGE is above 0 (gateway billing). |
| input | string | 9.1% | 100% | Text to detect language from (min 20 chars for accuracy) |
| mode | string | 9.1% | 0% | — |
Source: the input schema each server returns for detect_language, aggregated over the 11 index-tier servers; type and description are the values most servers use. Rebuilt every 6 hours.
Servers with detect_language
11 of 11 · 10 publishers · 11 answering live · most-starred first, 3 per publisher| # | Server | Publisher | Category | ★ | Live | How it describes detect_language |
|---|---|---|---|---|---|---|
| 1 | Text Analysis & Cleanup Tools (Tanod)tanod-labs · Documents & Knowledge | tanod-labs | Documents & Knowledge | 1 | yes | utilpeek: Detect the language of a text. To translate use translate_text. Returns the most likely language (ISO 639-1 and 639-3 code, name, confidence) and 3 alternatives, from an offline ensemble of lingua (Apache-2.0) and langid.py (BSD-2-Clause) over 75 languages; `reliable` is true only with at least 20 letters and confidence 0.6 or more. Short text is often flagged unreliable; text with no le |
| 2 | Embeddings, Rerank & Speech-to-Text (Tanod)tanod-labs · AI & Agents | tanod-labs | AI & Agents | 1 | yes | utilpeek: Detect the language of a text. To translate use translate_text. Returns the most likely language (ISO 639-1 and 639-3 code, name, confidence) and 3 alternatives, from an offline ensemble of lingua (Apache-2.0) and langid.py (BSD-2-Clause) over 75 languages; `reliable` is true only with at least 20 letters and confidence 0.6 or more. Short text is often flagged unreliable; text with no le |
| 3 | Olaverse Labolaverse-labs · Health & Science | olaverse-labs | Health & Science | — | yes | Identify the language of a text among 608 languages (built African-first; good on very short text). mode: "traffic" (user messages and chat; favours languages people actually use) or "coverage" (all languages equal, for building corpora). Returns the ISO 639-3 code, script, name, confidence and runners-up. |
| 4 | ImgKits MCPyichong1 · Media & Creative | yichong1 | Media & Creative | — | yes | Detect the language of up to 20,000 characters. Uses a local Unicode-script + stopword/diacritic heuristic; no upstream call. Returns a language code, confidence, reliability flag and alternatives. Billing: free by default (COST_DETECT_LANGUAGE=0). |
| 5 | IA-QA — 152 QA & Dev Tools for AI Agentsia-qa-com · AI & Agents | ia-qa-com | AI & Agents | — | yes | Detect the natural language of a text using n-gram frequency analysis and common word markers. Supports 15 languages: English, French, Spanish, German, Italian, Portuguese, Dutch, Russian, Chinese, Japanese, Korean, Arabic, Polish, Turkish, Swedish. |
| 6 | TidyData Toolstidydata-dev · Search & Web | tidydata-dev | Search & Web | — | yes | Language of a text. Detect language. Detect the language of any text: ISO 639-3 code, English name, confidence, reliability flag and top 5 candidates. Fast, no AI costs, works offline. |
| 7 | AgentIndex x402comallagency · Documents & Knowledge | comallagency | Documents & Knowledge | — | yes | Detect the language of a piece of text - free, no payment. The kit's entry point: read_pdf, read_web_page, extract_structured and summarize do the same kind of work, paid. |
| 8 | HebrewCore by baba Hebrewisaachorowitz · Health & Science | isaachorowitz | Health & Science | — | yes | Detect the dominant language, script and direction of a string, with one segment per language. Built for short, code-switched input (chat messages, search queries, voice transcripts): a brand or acronym such as "PayPal" or "API" inside a Hebrew or Russian sentence does not change the dominant language. Use it to pick `source_lang` or the reply language before translating. Latin script is tagged `e |
| 9 | DeriveAI x402 APIsderiveit33z-ship-it · APIs & Integrations | deriveit33z-ship-it | APIs & Integrations | — | yes | Detects language, script type, and Arabic dialect from any text. Supports Arabic (MSA, Gulf, Egyptian, Levantine, Maghrebi), English, French, Spanish, Turkish, Hindi. Also detects Arabizi (Latin-script Arabic) and mixed-language text. |
| 10 | Poly-Glot AI Workspacehmoses · Other | hmoses | Other | — | yes | Identify the primary language of a nonempty text snippet and map it to one of Poly-Glot's 38 supported language codes. Use when the source language is unknown before choosing an interface, output language, or translation workflow. Provide natural-language text in the text parameter (for example, '¿Dónde está la estación?'). Returns JSON with language, provider, and model. Does not translate or alt |
| 11 | NLP Tools - Sentiment, NER, Toxicity & Language Detectionfasuizu-br · AI & Agents | fasuizu-br | AI & Agents | — | yes | Detect the language of text. Supports 176 languages using fastText. Sub-1ms inference latency. Returns ISO 639-1 codes with confidence scores. Args: text: Text to identify the language of. top_k: Number of top language predictions to return (default: 3). Returns: dict with keys: - language (str): Top predicted language ISO 639-1 code - confidence (float 0-1): Confide |
Stars from GitHub as stored in the Serverdex index (re-read every 7 days per server); live = answered the last daily check of its hosted endpoint.