惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
Hugging Face - Blog
Hugging Face - Blog
F
Fortinet All Blogs
G
Google Developers Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
V
V2EX
Y
Y Combinator Blog
博客园_首页
Martin Fowler
Martin Fowler
博客园 - 司徒正美
MyScale Blog
MyScale Blog
宝玉的分享
宝玉的分享
B
Blog
有赞技术团队
有赞技术团队
A
About on SuperTechFans
量子位
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
酷 壳 – CoolShell
酷 壳 – CoolShell
Apple Machine Learning Research
Apple Machine Learning Research
M
MIT News - Artificial intelligence
阮一峰的网络日志
阮一峰的网络日志
Jina AI
Jina AI

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
One MCP server, four clients, zero translation dead ends
J Now · 2026-04-24 · via DEV Community

J Now

I wanted to tell my girlfriend something real in Farsi — not phrasebook real, actually real — and every translation tool gave me one answer with no indication of whether it was formal, casual, intimate, or strange. That's how konid started.

The tool returns 3 options for anything you want to say, ordered casual to formal, with the register of each option explained and the cultural nuance between them spelled out. It also plays audio pronunciation through your speakers directly (node-edge-tts, no external API key). Supports 13+ languages including Mandarin, Japanese, Korean, Arabic, and Hindi.

The part worth writing about here is the MCP setup. I built konid as an MCP server, which means the same installation runs across every client that speaks the protocol.

claude mcp add konid-ai -- npx -y konid-ai

Enter fullscreen mode Exit fullscreen mode

That one command wires it into Claude Code. Same server works in Cursor, VS Code Copilot, Windsurf, Zed, and JetBrains — add it once in whichever IDE you live in. For ChatGPT users, Developer mode + the endpoint https://konid.fly.dev/mcp connects it as a ChatGPT app. I also use it in Claude Cowork for non-code contexts, like drafting messages I actually want to send.

The practical effect: I'm not context-switching to a separate app or tab. I ask in whatever environment I'm already in. When I'm writing a work email in a language I'm still learning, the translation stays in my editor, with the nuance note right there. I read it, pick the right register, and actually absorb something about why one phrasing lands differently than another.

A literal translator gets you through the task. Seeing three options with context is what teaches you the language.

MIT licensed. github.com/robertnowell/konid-language-learning