Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
i18n for coding agents: extract, check and translate an app's text, with drafts a person approves
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"verbaly": {
"command": "npx",
"args": [
"-y",
"@verbaly/mcp"
]
}
}
}Run this in your terminal
claude mcp add verbaly -- npx -y @verbaly/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"verbaly": {
"command": "npx",
"args": [
"-y",
"@verbaly/mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"verbaly": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@verbaly/mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account AronSoto, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.79.0) reached the registry 4 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, Systemdox
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Your architecture in your agents' context: checks, specs, ADRs and docs over MCP, at write time.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Write your text in the code. Ship it in every language.
An i18n compiler and a tiny runtime for React, Vue, Svelte, Next.js, Nuxt, SvelteKit, Astro and plain HTML.
No key files to keep in sync, params typed from the text, and a CI gate that stops broken translations.
Most i18n tools ask you to invent a key for every sentence, write it in a file per language and keep the files in step with the code by hand. Verbaly turns that around:
// with key files: name it, write it in en.json, es.json, pt.json, keep them in sync
t('dashboard.welcome_back', { name });
// with Verbaly: write the sentence where it is used tWelcome back, ${name};
// and the compiler writes a stable key and a typed call for you t('ESsQIvlA', { name });
The runtime that ships is 3.35 KB gzip with zero dependencies, measured on every release by a gate in this repo (pnpm --filter verbaly size).
pnpm add verbaly @verbaly/vite
pnpm add -D @verbaly/compiler # the verbaly command: init, extract, check npx verbaly init
// vite.config.ts
import verbaly from '@verbaly/vite';
export default { plugins: [verbaly()] };
// anywhere in your app: extracted and typed on save
import { t, setLocale } from 'verbaly/app';
tHello ${name}; await setLocale('es'); // loads only the Spanish module
verbaly/app is your project's own module: the plugin writes it from your config, with your languages and catalogs already in it. Next.js, Nuxt, SvelteKit and Astro have their own one-line setup: pick yours in the row above, or read the full docs at https://verbaly-web.vercel.app/docs.
✍️ No key files You write the sentence. The compiler names it and keeps every language file in step with your code. 🧷 Typed from the text {name} , plurals, currency and dates come from the message itself, so a wrong or missing param fails to compile. 🛑 Broken ones never ship verbaly check catches a missing translation, and one that lost a {param} , a tag or a plural case, in plain words.
🪶 Small and fast Zero dependencies, one module per language, and a hot path benchmarked against i18next on every release. 🔄 Any workflow Plain JSON, XLIFF, CSV and gettext PO for translators, Android and iOS exports, and AI drafts a person approves. 🤖 Agent ready An MCP server, an Agent Skill and llms.txt , with drafts an agent can write but never approve.
npx verbaly-studio
Studio serves your project over localhost: what is missing, what is broken, what a machine wrote and where each text lives in your code. Your JSON files are the database and git is the history, a save runs the same validations as verbaly check, and it never edits your source text.
| Verbaly | i18next | Lingui | Paraglide | typesafe-i18n | |
|---|---|---|---|---|---|
| Type-safe keys & params | ✅ inferred from text | plugin/manual | partial | ✅ | ✅ |
| Runtime size (gzip) | 3.35KB, zero deps | 13.6KB (19.0 +react) | 2.2KB (3.3 +react) | compiled | 1.2KB |
| Setup | 1 Vite plugin | heavy config | macros + Babel/SWC | inlang project | generator |
| Key maintenance | none, extracted | by hand | extract → compile step | by hand | by hand |
| Dynamic / CMS content | ✅ real runtime path | ✅ | ✅ | ⚠️ weak | ✅ |
| Plain HTML (no framework) | ✅ DOM interpreter | ❌ | ❌ | ❌ | ❌ |
| Missing-translation gate | ✅ fails CI only | runtime warning | CI step | ✅ | ❌ |
| Broken-translation gate | ✅ fails CI only | ❌ | ❌ | ❌ | ❌ |
| Catalog format | plain JSON | JSON | PO/JSON | inlang format | TS files |
Sizes are min+gzip of each library's main entry with React external, measured with the same method on 2026-10-15.
claude mcp add verbaly -- npx -y @verbaly/mcp
The MCP server gives your agent the whole cycle as tools, with structured output and resources to read your config and catalogs. Machine translations stay drafts until a person approves them (verbaly review --approve, or Studio): approving is deliberately not a tool. The Agent Skill teaches the write, extract, check and translate cycle (npx degit AronSoto/verbaly/skills/verbaly .claude/skills/verbaly), and the docs publish llms.txt.
| Package | What it is |
|---|---|
verbaly | The runtime: t, Intl formats, locale helpers and the DOM interpreter |
@verbaly/compiler | Extraction, typed codegen, the gate and the verbaly command |
@verbaly/vite · @verbaly/unplugin | Bundler plugins: Vite, and webpack, Rollup, esbuild and Rspack |
@verbaly/react · @verbaly/vue · @verbaly/svelte | Framework adapters: hooks or composables plus |
@verbaly/next · @verbaly/nuxt · @verbaly/sveltekit | Server rendering: the language per request, hydration with no flash |
@verbaly/astro | Astro integration: .astro extraction and a static build per language |
@verbaly/mcp | MCP server: the translation cycle as tools for an agent |
@verbaly/studio | The local review panel above |
All of them share one version number, and every release is published from CI with npm provenance.
Editor: see the text behind a key on hover
Generated keys are hashes, so t('a1B2c3D4') in a diff tells you nothing. The i18n-ally extension shows the real text inline once you point it at your catalogs. Two files, no Verbaly config changes:
.vscode/settings.json
{
"i18n-ally.localesPaths": ["locales"], "i18n-ally.keystyle": "flat", "i18n-ally.sourceLanguage": "en", "i18n-ally.display
Only the beginning is shown; read the rest in the repo