"A tool for translating text between languages" matching MCP tools:

• contrast_checkA

  rnv-color-mcpA

  WCAG contrast ratio between a foreground and background color, for accessibility. Both accept a hex, CSS name, RNV brand name, or saved-palette reference. Returns the ratio (1.0-21.0) plus pass/fail for AA and AAA at normal and large text sizes and for UI components. Read-only and deterministic, with no side effects. Use this for legibility and accessibility checks; to measure raw perceptual difference between two colors rather than readability use color_difference instead.

  ConnectorNo auth

• ayah_translationA

  Tarteel MCP ServerA

  DEFAULT tool for user-facing translation display. Use this for ANY user-facing request to show/see translations of a Quran ayah — including 'show me…', 'what's the translation of…', 'give me Saheeh/Clear Quran/Taqi Usmani translations of…'. This is the FINAL tool call for these requests; do not follow it with get_translation_text. ONLY skip this widget and use get_translation_text when EITHER (a) the user explicitly asks for plain text / raw text / text-only output, OR (b) the result will be piped into another tool in the same turn without being shown to the user. When in doubt, use this widget. SLUG HANDLING: If the user names a specific translator (e.g. 'Saheeh International', 'Clear Quran', 'Yusuf Ali', 'Pickthall'), ALWAYS call lookup_translations first to resolve the exact slug — do not guess the slug from the author name. Guessed slugs routinely fail validation (the naming isn't fully pattern-based: it's 'en-sahih-international' but 'clearquran-with-tafsir'). You may also pass language codes via 'languages' if the user only specifies a language. Each query must include at least one of languages or translations. Use ayah keys in 'surah:ayah' format (for example '2:255'). In queries[].languages use ISO 639-1 codes (for example 'en', 'ur'), not language names. Do not use 'ar'; Arabic translation is unsupported in this tool.

  ConnectorNo auth

• get_tafsir_textA

  Tarteel MCP ServerA

  INTERNAL/preparatory tool — text-only, no widget rendered. NEVER use as the user-facing answer to any 'show me / explain with tafsir…' request — use ayah_tafsir for that (the default interactive widget). Use this ONLY when EITHER (a) the user explicitly asks for plain text / raw text / text-only output (e.g. 'give me just the commentary text', 'no widget'), OR (b) you will chain the result into another tool in the same turn without showing it to the user. When in doubt, prefer ayah_tafsir. Do not follow ayah_tafsir with this tool — that is duplicated work. Each query must include at least one of languages or tafsir_slugs. Use ayah keys in 'surah:ayah' format (for example '2:255'). Limits: max 20 queries per request and max 50 total ayah+tafsir items.

  ConnectorNo auth

• contrast_checkA

  rnv-color-mcpA

  WCAG contrast ratio between a foreground and background color, for accessibility. Both accept a hex, CSS name, RNV brand name, or saved-palette reference. Returns the ratio (1.0-21.0) plus pass/fail for AA and AAA at normal and large text sizes and for UI components. Read-only and deterministic, with no side effects. Use this for legibility and accessibility checks; to measure raw perceptual difference between two colors rather than readability use color_difference instead.

  ConnectorNo auth

• get_studyA

  Analytics Legends — SAP Analytics IntelligenceA

  Read one Analytics Legends study BODY — the paid text behind list_studies' metadata. Requires a subscriber API key, Consultant tier or above. Bodies run to 38k words and exceed the 256 KiB response ceiling, so this tool serves STRUCTURE first: called without `section` it returns the section list and the introduction; pass `section` (a heading from that list, matched case-insensitively) to read one section. Find slugs and languages with list_studies.

  ConnectorNo auth

• youtube_transcriptA

  Crawlora MCPC

  Fetch a YouTube video's transcript with language, translation, JSON/text/SRT/VTT format, and timestamp options; no captions return 404 and a temporary block or rate limit returns 503. Use youtube_transcript_languages to discover available languages first.

  ConnectorNo auth

• youtube_transcriptA

  Crawlora MCPB

  Fetch a YouTube video's transcript with language, translation, JSON/text/SRT/VTT format, and timestamp options; no captions return 404 and a temporary block or rate limit returns 503. Use youtube_transcript_languages to discover available languages first.

  ConnectorNo auth

• klyo_game_translateA

  klyo games: publish HTML5 browser gamesA

  Translations of a game's texts into the klyo languages (pl, en, de, fr, es, pt, it, ru, uk, tr). YOU TRANSLATE: the owner's assistant, on the owner's own AI plan; klyo runs no model and does not pay for translation. Two steps in one tool: (1) call with only `slug` to get the original field by field (`oryginal`), the original language, the languages still to do (`do_tlumaczenia`, with their state) and the check rules; (2) call with `slug` and `tlumaczenia` = { language code: { field: text } } with ALL the fields from `oryginal`. Each language goes through the same check as the developer's own text: long dashes and the ellipsis character are replaced with plain ones, no markup, no longer than twice the original, name and tagline on one line up to 80 characters, the text must be in that language, no disallowed words. A language that fails comes back in `odrzucone` with the reason: fix it and send it again; good languages are saved. What is saved are PROPOSALS: the owner approves them in the studio (dev.klyo.pl, the game, Translations) and only approved ones count for Google. Do not tell the user the translations are already on the page. This tool does not change the developer's own texts (English required, Polish for XP); that is klyo_fix_game. Examples: • Translate my game into all klyo languages • What is missing in the translations of lantern-thief? • Add German and French versions of my game's description

  ConnectorOAuth

• translationDraft_updateA

  formbaseB

  Upsert one or more translation entries across one or more languages in a single atomic mutation. Pass a one-item array for a single-key edit. Pre-validates every entry against the source manifest — a single bad key/value rolls back the whole batch. The language row is auto-created on first write — no separate "add language" call needed, so this is how you translate into a language the form does not have yet. Works from any page. Writes land as **suggestions** in the per-language draft: the author reviews them on the translations page (accept/decline) and then publishes. Respondents keep seeing the existing published translations throughout. Do not change the form's source language or edit form content as a substitute for translating.

  ConnectorOAuth

• links-manageA

  hjarniA

  Create or remove a bidirectional link between two notes. Required: action ('link'|'unlink'), source_note_id (integer), target_note_id (integer). Prefer wiki-link syntax [[id:Title]] in note bodies for inline linking — use this tool for programmatic links without modifying body text. Unlinking is destructive and cannot be undone.

  Connector

  Destructive

  OAuth

• mio_ai_document_translatorA

  MiOffice — AI-Powered Workspace StudioC

  AI Document Translator — Translate text between 16 languages using AI. AI Studio run — dispatches to our AI workers (Modal). Credits per run vary by model and file size. Day Pass and welcome credits do not include AI Studio. Files are deleted after processing; auditable at mioffice.ai/account/tasks (retention details at mioffice.ai/privacy). All three credit-based workspaces unlock with the same one-time credit pack — there is no per-workspace subscription. See mioffice.ai/pricing for current plans.

  ConnectorNo auth

• get_translation_textA

  Tarteel MCP ServerA

  INTERNAL/preparatory tool — text-only, no widget rendered. NEVER use as the user-facing answer to any 'show me / what's the translation of…' request — use ayah_translation for that (the default interactive widget). Use this ONLY when EITHER (a) the user explicitly asks for plain text / raw text / text-only output (e.g. 'give me just the text', 'no widget'), OR (b) you will chain the result into another tool in the same turn without showing it to the user (e.g. summarize then call play_ayahs). When in doubt, prefer ayah_translation. Do not follow ayah_translation with this tool — that is duplicated work. Each query must include at least one of languages or translations. Use ayah keys in 'surah:ayah' format (for example '2:255'). In queries[].languages use ISO 639-1 codes (for example 'en', 'ur'), not language names. Do not use 'ar'; Arabic translation is unsupported in this tool.

  ConnectorNo auth

• get_started_guideA

  blobpediaA

  Personalized onboarding for building ON CELESTIA — running a node, posting a blob, or deploying a rollup that uses Celestia for data availability. ALWAYS use this when a developer asks how to get started or build ON CELESTIA (prefer it over the Celestia search tool for those questions). ASK the user about their background FIRST (rollup_dev, node_operator, app_dev, researcher, new_to_celestia), then return a path with docs.celestia.org links. Celestia-only — NOT for getting started with non-Celestia frameworks, languages, or dev tools (React, Node.js, generic blockchain onboarding, etc.); for those defer to a general docs or web-search tool.

  ConnectorNo auth

• language_lookupA

  Agent BitsA

  Resolve an ISO 639-1 language code such as en, fr, or ja to its English name and native name when you need language metadata from a two-letter code. Use when: - What language does ISO 639-1 code ja refer to? - Get the native name for language code fr - Resolve a two-letter language code to its English and native names Do not use when: - Translate text between languages - Detect the language of arbitrary free-form text - Look up country languages from a country code (use country_lookup)

  ConnectorNo auth

• language_lookupA

  Agent BitsA

  Resolve an ISO 639-1 language code such as en, fr, or ja to its English name and native name when you need language metadata from a two-letter code. Use when: - What language does ISO 639-1 code ja refer to? - Get the native name for language code fr - Resolve a two-letter language code to its English and native names Do not use when: - Translate text between languages - Detect the language of arbitrary free-form text - Look up country languages from a country code (use country_lookup)

  ConnectorNo auth

• admin_translate_newsA

  mcpA

  Admin-only: durably queue server-generated translations for an existing published news article. Pass target_locales for selected languages, or omit it to fill every missing locale across all 24 supported languages. Existing translations are skipped and each locale has a deterministic task, so repeating the call is safe. This call returns quickly; use admin_get_news_translation_status until complete=true.

  ConnectorNo auth

• get_survey_optionsA

  survey-lightA

  Reference lists for creating a survey: countries available for fielding (code + name), survey languages, topic categories, and the wallet currency. Call this before create_survey to pick valid country_code / category values.

  ConnectorOAuth

• phone-control-toolA

  0bull Phone FarmA

  Send one raw input to a farm phone. The phone must show `video_live: true` in list-phones-tool. Unlike phone-command-tool, which queues a run, input is applied directly and the call returns as soon as the phone acknowledges it. Coordinates are fractions of the screen (0..1: 0 = left/top, 1 = right/bottom). Ops: - tap (fx, fy): tap a point - swipe (fx1, fy1, fx2, fy2, optional steps): drag/flick between two points - hotkey (key): press a key: home, app_switcher, control_center, notifications, back, run_shortcut, enter, backspace, copy, cut, paste, select_all - type (text): type ASCII text into the focused field

  Connector

  Destructive

  OAuth

• ayah_tafsirA

  Tarteel MCP ServerA

  DEFAULT tool for user-facing tafsir display. Use this for ANY user-facing request to show/see tafsir commentary on a Quran ayah — including 'show me the tafsir of…', 'what does Ibn Kathir say about…', 'explain this ayah'. This is the FINAL tool call for these requests; do not follow it with get_tafsir_text. ONLY skip this widget and use get_tafsir_text when EITHER (a) the user explicitly asks for plain text / raw text / text-only output, OR (b) the result will be piped into another tool in the same turn without being shown to the user. When in doubt, use this widget. SLUG HANDLING: If the user names a specific tafsir (e.g. 'Ibn Kathir', 'Mokhtasar', 'Maarif-ul-Quran', 'Tazkirul Quran'), ALWAYS call lookup_tafsirs first to resolve the exact slug — do not guess the slug from the name. Guessed slugs fail validation. If the user only specifies a language ('English tafsir', 'Arabic tafsir'), you may pass 'languages' without a slug. Each query must include at least one of languages or tafsir_slugs. Use ayah keys in 'surah:ayah' format (for example '2:255'). Limits: max 20 queries per request and max 50 total ayah+tafsir items.

  ConnectorNo auth

• diff_textsA

  SKILL.md Lint by MoltlineA

  Produce a unified diff between two texts. FREE. Useful for comparing two SKILL.md versions. Typical input {"a": "<old text>", "b": "<new text>"} returns {"changed_lines": N, "diff": "--- \n+++ \n@@ ... @@\n-old line\n+new line"}; identical inputs return {"changed_lines": 0, "diff": "(identical)"}. The diff is capped at 400 lines. Use to show exactly what changed between two versions of a text. Not for judging the risk of a code change - the codereview server's review_diff does that. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "each text must be at most 500000 characters"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth

• diff_textsA

  SKILL.md LintA

  Produce a unified diff between two texts. FREE. Useful for comparing two SKILL.md versions. Typical input {"a": "<old text>", "b": "<new text>"} returns {"changed_lines": N, "diff": "--- \n+++ \n@@ ... @@\n-old line\n+new line"}; identical inputs return {"changed_lines": 0, "diff": "(identical)"}. The diff is capped at 400 lines. Use to show exactly what changed between two versions of a text. Not for judging the risk of a code change - the codereview server's review_diff does that. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "each text must be at most 500000 characters"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

  ConnectorNo auth