"Using local LLMs for code writing, reviewing, and rule generation" matching MCP servers:

Delegates mechanical text-to-text tasks to a local LLM to save Claude subscription quota, reading files server-side so large content never enters Claude's context.

Provides offline translation across 200+ languages using a local NLLB-200 model, with no data leaving your machine.

Adds a single MCP tool that lets Codex request local, read-only draft transformations of user-provided text, using a local Ollama model for translation, summarization, rewriting, extraction, and classification.

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.

Enables bidirectional lookup of Mi'kmaq and English words with definitions and examples, and provides tools for learning and dictionary statistics, integrating seamlessly with AI-powered IDEs.

Lets AI agents read and write the Calibre Ebook Translator plugin's translation cache chunk by chunk, enabling direct book translation workflows without manual copy-paste.

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 internationalization tasks such as language detection, hardcoded string extraction, translation JSON analysis, plural rule generation, and locale-aware formatting through the Model Context Protocol.

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

MCP server that automates WebGAL game development tasks such as resource management, script editing, documentation lookup, and AI-powered voice generation using LLMs.

Provides guidelines for writing proper apologies based on the situation, relationship, and severity. Returns structured prompts that help LLMs generate sincere and appropriate apology letters in Korean.

MCP server that provides grounded Arabic dictionary lookup, enabling AI agents to search word roots, inflections, and meanings from real dictionary data.

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.

MCP server for translating PDFs using pdf2zh-next, preserving document context by extracting all text segments for LLM translation at once.

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 AllVoiceLab Model Context Protocol (MCP) server, supporting interaction with powerful text-to-speech and video translation APIs.

Manage app strings, locales, and A/B string variants, then publish Ed25519-signed string bundles for over-the-air text updates in iOS, Android, web, and React Native apps.

English-first Korean equity intelligence MCP — translates Korean DART filings, foreign-holder 5%-rule flows (BlackRock / Vanguard / Norges / GIC plus 16 more), activist filings (KCGI / Align / ValueAct / Elliott), and KRX industry news to English on demand. 7 MCP tools, OSS self-host under AGPL-3.0.