Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Manage app translations: find and create keys, draft translations, commit and ship OTA releases.
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 …”.
Works in Claude on the web, desktop and mobile:
https://mcp.litei18n.com/mcpRun this in your terminal
claude mcp add --transport http litei18n https://mcp.litei18n.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"litei18n": {
"url": "https://mcp.litei18n.com/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": {
"litei18n": {
"type": "http",
"url": "https://mcp.litei18n.com/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.
ChatGPT connects only to servers on the internet:
https://mcp.litei18n.com/mcpMenu names can differ slightly by plan and over time.
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.
The server asks you to sign in before it lists its tools.
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 against the domain litei18n.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 1201 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (2.0.0) reached the registry 4 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
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.
Manage your app's translations from Claude, ChatGPT, Cursor, VS Code and any other AI app that speaks the Model Context Protocol.
LiteI18n stores your app's translation keys, lets you draft and review translations, and ships them to your app over the air (OTA), with no app store release. This hosted MCP server lets an AI agent do that work for you: find keys, add new copy, draft translations, publish them and ship a release.
https://mcp.litei18n.com/mcp
Up-to-date guides with copy buttons and one-click installs: [litei18n.com/agents](https://litei18n.com/agents).
litei18n, paste https://mcp.litei18n.com/mcp, click Continue twice, then Add.On Team and Enterprise plans, an Owner adds it first under Organization settings → Connectors; members then click Connect.
litei18n, paste the link, choose OAuth, confirm the warning and click Create as a plugin. Sign in to LiteI18n.If + is missing, your workspace admin may need to allow custom MCP servers.
claude mcp add --transport http litei18n https://mcp.litei18n.com/mcp
Then type /mcp, choose litei18n and sign in. To get the agent skill as well, install the plugin instead (see Agent skill).
codex mcp add litei18n --url https://mcp.litei18n.com/mcp
codex mcp login litei18n
gemini extensions install https://github.com/Aevum-Technology/litei18n-mcp
This adds the MCP server and the agent skill together. Start gemini, then run /mcp auth litei18n and sign in.
Install in Cursor, or add this to .cursor/mcp.json:
{
"mcpServers": { "litei18n": { "url": "https://mcp.litei18n.com/mcp" } } }
Install in VS Code, or add this to .vscode/mcp.json:
{
"servers": { "litei18n": { "type": "http", "url": "https://mcp.litei18n.com/mcp" } } }
Add this to opencode.json, then run opencode mcp auth litei18n:
{
"mcp": { "litei18n": { "type": "remote", "url": "https://mcp.litei18n.com/mcp" } } }
Add this to ~/.config/devin/mcp_config.json (on Windows, %APPDATA%\devin\mcp_config.json), save, and sign in when asked:
{
"mcpServers": { "litei18n": { "serverUrl": "https://mcp.litei18n.com/mcp" } } }
Add this to ~/.gemini/config/mcp_config.json, then open Agent settings → Customizations and click Authenticate next to litei18n. Paste the code your browser shows and click Submit.
{
"mcpServers": { "litei18n": { "serverUrl": "https://mcp.litei18n.com/mcp" } } }
Open Settings → AI → MCP Servers, click Add Server, choose Add Remote Server and paste the link.
Add a remote MCP server using Streamable HTTP with the link above. Sign in when your browser opens.
promo.summer_2025 keys."| Tool | What it does | Kind | Permission |
|---|---|---|---|
list_projects | List the projects this connection can reach, with languages, key count and permissions | Read | — |
list_keys | Find, search or fetch keys with their live translations and drafts | Read | keys:read |
create_key | Create up to 100 keys, optionally with first translations (saved as drafts) | Write | keys:write (+ translations:write) |
upsert_draft | Save draft translations for up to 500 key and language pairs | Write | translations:write |
delete_key | Delete a key. A published key is removed at the next publish and can be restored until then | Destructive | keys:write |
restore_key | Undo a pending key deletion, before publishing | Write | keys:write |
commit_drafts | Publish drafts as live translations (optionally one language) | Destructive | drafts:commit |
list_releases | List the project's OTA releases | Read | releases:read |
create_release | Ship the latest published translations to your apps over the air | Destructive | releases:write |
Every tool declares a title and the standard MCP safety hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint), so your AI app can ask before it publishes or deletes. Results are structured data matching each tool's output schema. Text written by project members (key names, translations, drafts) is marked as content, never as instructions.
When you approve a connection you choose, for each project, what the AI app may do:
| Scope | Allows |
|---|---|
keys:read | Find and read keys |
keys:write | Create, delete and restore keys |
translations:read | Read translations and drafts |
translations:write | Save draft translations |
drafts:commit | Publish drafts |
releases:read | List releases |
releases:write | Create OTA releases |
Presets: Read only (all reads), Read and write (all reads, key and translation writes, publishing), Full access (everything, including releases).
skills/litei18n is an Agent Skill that teaches your agent the LiteI18n workflow: look before writing, drafts versus publishing, when to ask first, and how to load OTA translations in your app with a safe fallback. It works with the MCP server above; it is optional but makes agents more careful and more accurate.
Claude Code (plugin: MCP server and skill together)
/plugin marketplace add Aevum-Technology/litei18n-mcp
/plugin install litei18n@litei18n
Gemini CLI (extension: MCP server and skill together): see Gemini CLI.
Any agent that supports skills (Claude Code, Codex, Cursor, OpenCode and others)
npx skills add Aevum-Technology/litei18n-mcp --skill litei18n
Claude.ai and the Claude desktop app: download this repository as a ZIP, then upload the skills/litei18n folder (zipped) under Customize → Skills.
Manually: copy skills/litei18n into your agent's skills folder, for example ~/.claude/skills/litei18n or .agents/skills/litei18n.
Scripts and CI jobs can call the same link with a LiteI18n API token instead of signing in. Create one under API Tokens in your workspace and send it as Authorization: Bearer litei18n_…. Keep it in your CI's secret store, never in code or chat.
| You see | What to do |
|---|---|
| Asked to sign in again | The connection was disconnected or expired. Sign in from your AI app again. |
| "No access to this project" | The project was not selected when you approved. Reconnect and tick it. |
| "Permission denied" | The connection lacks that permission for the project. Reconnect with a higher access level. |
| "Your plan does not allow this action" | Creating OTA releases needs the Starter plan or above. Upgrade under Billing. |
| "This workspace has been suspended" | Contact support. Access returns once the suspension is lifted. |
| Too many requests | Each connection may make 60 requests a minute. Wait a moment and try again. |
The server only acts inside the workspace and projects you approved, and only with the permissions you chose. Your AI app never sees your LiteI18n password.
This repository holds the public documentation, the MCP Registry entry (server.json), the Claude Code plugin, the Gemini CLI extension (gemini-extension.json) and the agent skill. The hosted service itself is operated by Aevum Technology LTD and is not open source. The contents of this repository are released under the MIT License.