"QA review sentinel test marker" matching MCP servers:

prevents llm from overload, freeze and oscillation

Translation QA for i18n locale files. Deterministic validators — missing keys, placeholder drift, collapsed plurals, glossary breaches — that need no API key, plus a review tool that hands translation pairs and judging criteria back to the calling agent, so meaning-level review runs on the model your client already has. Translation with your own LLM key is optional. JSON, Flutter .arb, Apple .

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.

Assists MDN Japanese translation tasks by automating file copying from English content, synchronizing source commits, and performing guideline-based reviews.

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.

Provides text translation capabilities using the Niutrans API, supporting 455+ languages with code/alias mapping through a language catalog resource.

Spanish dialect localization MCP server and CLI. It translates and QA-checks content across 25 regional variants with register control, structure preservation, and adversarial quality gates.

Translates Korean KakaoTalk messages to natural Japanese with pronunciation and expression breakdowns, corrects user-written Japanese sentences, explains expressions, and generates review cards and quizzes for beginner learners.

Counts characters and words in both Japanese and English text files, with special handling for Japanese morphological analysis and proper character counting excluding spaces and line breaks.

A read-only server that gives MCP clients access to a user's WaniKani progress and reference data through the official API v2, answering questions about upcoming reviews and lessons, kanji assignments by level, review accuracy, and saved notes or synonyms. It runs locally over stdio without storing data or modifying WaniKani.

Enables users to connect their Maimemo account through a local MCP to query vocabulary, manage cloud wordbooks and learning materials, review study progress, and perform study actions via natural language.

Enables MCP clients such as Claude Desktop and Cursor to read tracked app keywords, opportunities, account apps, and action plans; generate or translate listing copy; review results; and apply accepted title, subtitle, keywords, or short-description fields to an editable draft without publishing to Apple or Google.

MCP server for the Humanread novel publishing platform, enabling AI agents to upload, format, preview, review, translate, and publish novels in Markdown or safe HTML.

An MCP server that lets coding agents drive the full PDF-to-lesson pipeline — ingesting, planning, storyboarding, translating, narrating, QA-ing and exporting — or author lesson beats themselves while the server validates and renders them. It enables agents to produce offline, animated, narrated, interactive books with in-picture questions.

Enables learners to quiz themselves on French word meanings from textbook units and daily review sets, with interactive card flips, self-scoring, and per-user cloud progress storage.

Enables AI agents, developers, and CI pipelines to run deterministic, offline localization QA — pseudolocalization, locale linting for separators/dates/placeholders/RTL, and glossary enforcement across 20 locales — without any network access or API key. When an OpenAI-compatible endpoint is configured, it can also translate into multiple locales and lint the results, or otherwise emit structured translation jobs instead of fabricating translations.

Enables an AI assistant to act as the memory of a personal English-learning app: read progress and words due for review, run short practice conversations, and store sentences, corrections, new words, rubric scores, and checked exercises back to the user's dashboard. Also lets the assistant grow the flashcard deck and adjust word familiarity, which reschedules spaced-repetition reviews.

Enables source-verified lesson preparation from a local al-Maktaba al-Shamila 4 library by fetching and double-checking complete passages, anchoring citations, resolving printed pages, managing persistent projects, labeling lesson units, optionally translating with human review, and exporting to Markdown, HTML, or JSON.

Enables a parent assistant to delegate independent text tasks such as summarization, translation, or code review to an OpenAI-compatible Chat Completions model through MCP tools and receive the generated text, model metadata, finish reason, truncation status, and token usage.

Lets a coding agent find, translate, validate and review an app's existing localization files (Android strings.xml, Apple String Catalogs, gettext) directly in the repo, supplying code usage, comments, glossary and voice notes as context. Placeholders, plural forms, escaping and markup are checked in code before any translation is written, and results land as reviewable drafts that never overwrite hand edits or approved work.

Translates Japanese text into English using the Textra API service, enabling LLMs with limited Japanese understanding to process Japanese instructions.

Provides comprehensive text analysis capabilities including character counting, word statistics, character type analysis, and text length validation for Korean and English text. Supports AI agents in analyzing and validating text content with detailed statistics and Unicode support.

A ModelContextProtocol server providing high-quality translation services with a three-stage translation workflow (analysis, segmented translation, full-text review) that supports multiple languages and integrates with Claude and OpenAI-compatible models.