"AWS instance metadata service endpoint URL" matching MCP servers:

Provides multilingual text translation capabilities using Baidu Translate API with support for language detection and advanced features like context filling and zero-width character obfuscation for testing agent robustness.

Enables translation of PowerPoint presentations to multiple languages using AWS Bedrock models while preserving formatting. Supports 8 languages including Chinese, Japanese, Korean, and major European languages.

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.

Enables translation, language detection, and language list retrieval via MCP tools, acting as a thin wrapper over a self-hosted LibreTranslate instance.

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.

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.

Translates PowerPoint presentations while preserving formatting using Amazon Bedrock models, available as both a standalone tool and a FastMCP service for AI assistants like Amazon Q Developer.

Enables Claude to translate, search, and manage Obsidian notes directly through the Model Context Protocol. It features automatic backups, CRUD operations, and protects metadata and code blocks during the translation process.

An MCP server that integrates Kagi Translate as tools for translation, URL translation, and proofreading, requiring a Kagi API key.

A custom MCP protocol service that enhances AI models by providing multilingual translation capabilities and resource management, allowing for automatic text extraction and translation through external APIs.

Enables AI video dubbing from any MCP-capable agent: upload a video or provide a URL, submit a dubbing job, poll progress, and download the finished MP4.

Enables Japanese-to-Korean manga translation via a two-stage pipeline (Hy-MT2 and Qwen) through an MCP endpoint, with a headless web UI and JSON HTTP API.

Connects MCP clients to a self-hosted LanguageTool HTTP instance over stdio, letting them proofread text for spelling, grammar, punctuation and style issues and to list the languages the instance supports. Returns a Markdown report grouped by category with correction suggestions, and supports language selection, stricter checking, and rule enabling/disabling.

Lets any MCP client generate language-learning flashcard decks, complete with pictures and covers, and custom card templates/looks, returning a link that adds the result to the user's collection. Runs over Streamable HTTP at a public endpoint with no account or API key required.

MCP server that translates AI-assistant-style text into plain English via the Declaude service, supporting authentication and quota management.

Enables AI agents to extract YouTube video metadata and generate high-quality multilingual transcriptions with voice activity detection, supporting 99 languages with translation capabilities and intelligent caching.

MCP server for the Globalize localization platform: create translation projects, add languages, manage glossaries and style guides, connect repositories, and track translation jobs from any MCP client. Available as a hosted Streamable HTTP endpoint and as an open-source TypeScript package in the mcp-server directory.

Word Orb is a language enrichment MCP server. 50,000+ words with IPA, definitions, etymology, translations in 47 languages with native script, gender equity guidance, and AI identity ethics. 3ms edge response. Tools: word_enrich, word_ethics, agent_speak. URL: https://mcp.wordorb.ai/mcp

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.

Provides open-source machine translation capabilities, including language detection and listing supported languages, via a customizable LibreTranslate endpoint.