A lightweight Gradio application that analyzes text for sentiment (positive/negative) and sarcasm detection using Hugging Face Transformers, designed to run on CPU and compatible with the MCP server architecture.
This server implements the Model Context Protocol to provide sentiment analysis of text, returning polarity, subjectivity, and overall assessment (positive, negative, or neutral).
Integrates local language models (like Qwen3-8B) with MCP clients, providing tools for chat, code analysis, text generation, translation, and content summarization using your own hardware.
Provides translation and language detection tools to AI agents, processing text, audio, and Google Meet recordings with emotional voice style preservation via Google's Gemini Live API.
Search Japanese onomatopoeia by scene, not by spelling. 161 entries with nuance explained in Japanese and English. Fully offline MCP server, no API key required.
AI localization from your editor — translate an app's string files into 46 languages with placeholder-safe, reproducible output. Eleven formats (JSON, .arb, .po, .strings, Android XML and more), and every translation is read back and checked before it lands.
A local-first multilingual dictionary, thesaurus, translation, lexical-relations, semantic-neighbour, and English wordplay server for the Model Context Protocol (MCP). It operates fully offline with read-only query access and no data mutation while running.
Translation quality evaluation MCP Server powered by xCOMET. Provides quality scoring (0-1), error detection with severity levels, and optimized batch processing for AI-assisted translation workflows.
Official Paxa Labs MCP server: Thai, English and Mandarin text-to-speech with local playback, voice design from a text description, speech-to-text with subtitles, translation into Thai, and document OCR with field extraction.
Integrates the levelang.app translation API with AI assistants to provide translations constrained to specific learner proficiency levels. It supports multiple languages and allows users to control translation styles and moods while dynamically discovering available language configurations.
Enables fetching YouTube video transcripts from any URL without API keys, browser, or OAuth, with honest error reporting for missing transcripts and support for multiple languages, formats, and resilient provider fallbacks.
The i18n cycle of a JavaScript project as tools: extract the texts written in code, list missing translations and write machine translations as drafts that a person approves. Works with React, Vue, Svelte, Next.js, Nuxt, SvelteKit and Astro.
A language expression coach MCP server that provides native-sounding translations with cultural context, tone notes, and audio pronunciation for over 13 languages.
An MCP server that provides LLM agents with full access to the Texterify translation management API. It enables users to search, create, update, and delete translation keys and their values directly through natural language within their development environment.
Enables law firms and legal professionals to turn Arabic and English contract files into structured, citable context, with clause segmentation, date conversion across Hijri and Gregorian calendars, party extraction, and anchor-based verification, all without API keys or network calls.
Provides AI models with tools to proofread and format Chinese text before delivery, covering typos, punctuation, casing, spacing, and platform-specific character limits. It runs as a zero-dependency MCP service so the model checks and fixes its own Chinese writing automatically.
Products, social posts, search results and AI answers from Amazon, TikTok, Google, ChatGPT and more, as MCP tools. Code mode: the model writes TypeScript against a typed client, run in a sandbox.
Enables Claude and other MCP clients to look up German Wiktionary entries directly, checking whether words exist and returning parts of speech, gender, plural and case forms, verb conjugations, adjective declensions, IPA, meanings, etymology, synonyms and examples. It also supports full-text title search with spelling suggestions and retrieval of raw page wikitext for anything the structured tools omit.
Enables MCP clients to replace hardcoded text in source files with i18n resource keys, with support for previewing changes, profiles, resource sets, and machine translation.
Enables an AI agent to inspect, repair, retime, convert, merge/split, and search SRT, WebVTT, and ASS subtitle files entirely offline, with exact-fraction resync, dry-run fixes, and honest encoding detection. Translation is handled by the agent itself through a chunk/apply contract that preserves timing and flags lost tags.
Checks AI-written Japanese business text for double honorifics (二重敬語) and the honorific chains the 「敬語の指針」 guideline deems inappropriate, returning each offending span with its reason and suggested fix, and can rewrite the text with those fixes applied. Runs offline and read-only, so agents get the same deterministic answer on every pass.
An intelligent PDF translation assistant specializing in academic papers with mathematical formulas, enabling context-aware translation with layout preservation.
Provides local anonymization of Czech legal documents by replacing sensitive entities with pseudonyms to ensure privacy during LLM interactions. It allows users to safely process documents like contracts and judgments by keeping original data offline and facilitating local deanonymization.
Provides text translation capabilities powered by NiuTrans API with support for 455+ languages. Includes translation tools and language catalog resources for seamless integration with MCP clients.
Seoul-area subway routes in English, Korean, Japanese and Chinese with transfers, boarding direction and fares, plus Korean public holidays and visitor guides. Works offline with no API key.
Enables OCR of local images through a public endpoint and writes the extracted text to a specified file, optimized for Tibetan, Sanskrit, and Devanagari input with optional transliteration.
Translate Python between English and your language, with round-trip verification. Pack-based and reviewed, not model-guessed: translate files both ways, look up how terms render, check identifier names, and report how legible a codebase is in a language, all locally with uvx legesher-mcp.
Enables transcription and subtitling of Tunisian Derja mixed with French and English, speech and voiceover generation, translation, and Arabizi–Arabic script conversion inside MCP clients. It also supports speaker diarization, subtitle translation, transcript search, and audio editing.
Enables an AI assistant to place user-approved phone calls in the callee's language through your own Bland or Twilio account, with language detection, script generation, cost estimates, and safety guard rails. Includes a preview-then-confirm gate, plus call status, transcripts, and summaries.
Provides AI agents with local Dutch spelling and word validation using OpenTaal/hunspell, plus detailed word information from woordenlijst.org. It enables checking full texts or individual words and retrieving linguistic details for Dutch writing tasks.
Enables agents to translate text-selectable PDFs into bilingual PDFs with original formulas preserved, layout reflow, and bidirectional hover highlighting in Adobe Acrobat. The agent claims pending sentence batches, submits translations back through the server's tools, and receives dual, monolingual, and plain PDFs plus coverage and highlight reports.
Enables LLMs to understand and work with shipbuilding terminology (Korean/English), including search, translation, and explanation of terms across 14 categories with 364 terms.
Enables AI assistants and MCP clients to look up Gujarati words in real dictionary data for meanings, synonyms, idioms, and inflected forms, with source attribution and typo suggestions. It also tells the model when a word is not found so it avoids guessing.
An MCP server that automatically translates Android app string resources to multiple languages by detecting changes in default strings.xml files using Git diff. It supports batch translation, preserves formatting placeholders, and works with multiple Android modules.
Enables AI agents to translate PDFs, scanned PDFs, DOCX, EPUB files and page images into 70+ languages while rebuilding the original layout, with OCR for scans and free uploads that return an exact price before anything is charged. Agents can then start the job, poll its progress, and download the finished file in its original format.
MCP server for TERMDAT, the terminology database of the Swiss Federal Administration, giving AI agents officially validated designations of Swiss authorities, departments, and legal acts across DE/FR/IT/EN with source references and validation status.
Read-only MCP server over the multilingual pick-up line corpus of rumors.app (Tagalog, Brazilian Portuguese, Indonesian, Hindi and more), curated by native editors with literal English glosses. Stdio and Streamable HTTP transports.
Enables comparing local JSON/YAML locale files to find missing or extra keys against a base locale, detect empty, null, or whitespace translations, and list flattened dot-path keys for a single file. Works entirely on local files with no network calls or translation APIs.
MCP server for managing i18n JSON translation files. Provides Claude with structured read/write access to translation files for adding keys, checking coverage, and finding duplicates.
Dub YouTube videos, local videos or SRT files into other languages with one cloned voice per speaker, synced SRT captions and YouTube multi-language audio tracks.
Enables batch translation of arXiv, DOI, or paper-page LaTeX sources into Simplified Chinese and compilation of Chinese PDFs via XeLaTeX, using DeepSeek's deepseek-flash model with glossary, structure validation, resume, and QA.
Enables AI agents to inspect, audit and safely edit locale JSON files across flat, nested, and namespaced layouts without loading whole files into the model context, with compact token-efficient reads and write paths that cannot drop keys or overwrite silently. Ships ten tools plus slash-command prompts for project info, key search, reference lookup, translation upserts, and missing-translation audits.
AI-powered speech tools by Brainiall: pronunciation assessment with phoneme-level feedback, speech-to-text with language detection, and text-to-speech with multiple voices.
Enables integration of DeepSeek's language models with MCP-compatible applications, offering features like chat completion, custom model selection, and parameter control for enhancing language-based interactions.
Enables fetching and analyzing YouTube video comments and replies through the YouTube Data API. Supports sorting by relevance or time and returns structured JSON data for comment analysis, summarization, and translation tasks.
Enables AI agents to access paid tools like crypto prices, weather, translation, and web intelligence via per-request USDC payments on Base, with no API keys or subscriptions.
Enables AI agents to look up Persian words on Abadis and Vajehyab at once, returning Dehkhoda, Moein and Amid meanings, synonyms and antonyms, pure-Persian equivalents, English, Arabic and Turkish translations with example sentences, spelling autocomplete, and Persian first names. It is read-only, requires no API key, and runs over stdio in Claude, Cursor, Copilot or any other MCP client.
Translates Sinhala or Singlish instructions into precise English technical specifications using Google Gemini AI, enabling Sinhala-speaking developers to code in their native language.
Enables AI assistants to run accurate, offline Bangladesh calculations in English or Bangla — income tax with rebates and minimum tax, taka amounts in words for cheques and invoices, mobile number validation and operator detection, loan EMI, DPS/FDR savings growth, safe maths expressions, and digit conversion. Every tool is a local read-only computation, requiring no network access or API keys.
Enables agents to keep per-language JSON locale files synchronized with an English source by translating changed keys via MyMemory, validating placeholder tokens, pruning deleted keys, and flagging failures for manual agent translation.