Connects Claude and other MCP clients to Nativ's localization API. Exposes eight tools including translate, translate_batch, and search_translation_memory, plus prompts for guided localization workflows. Every translation checks your translation memory first and applies your brand voice and style guides automatically. You can add approved translations back to TM, search existing entries with fuzzy matching, and batch-localize i18n strings in one call. Install via npx with just an API key from dashboard.usenativ.com. Useful when you're localizing UI strings, marketing copy, or documentation and want consistency with past translations without leaving your editor.
mcp-name: io.github.Nativ-Technologies/nativ
AI-powered localization for any MCP-compatible tool — Claude Code, Cursor, Windsurf, and more.
Nativ is a localization platform that uses AI to translate content while respecting your brand voice, translation memory, glossaries, and style guides. This MCP server brings Nativ's full localization engine into your AI coding workflow.
Sign up at dashboard.usenativ.com, go to Settings → API Keys, and create a key. It looks like nativ_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.
Add to your MCP configuration:
~/.claude/claude_desktop_config.json){
"mcpServers": {
"nativ": {
"command": "npx",
"args": ["-y", "nativ-mcp"],
"env": {
"NATIV_API_KEY": "nativ_your_api_key_here"
}
}
}
}
.cursor/mcp.json in your project or ~/.cursor/mcp.json globally){
"mcpServers": {
"nativ": {
"command": "npx",
"args": ["-y", "nativ-mcp"],
"env": {
"NATIV_API_KEY": "nativ_your_api_key_here"
}
}
}
}
{
"mcpServers": {
"nativ": {
"command": "npx",
"args": ["-y", "nativ-mcp"],
"env": {
"NATIV_API_KEY": "nativ_your_api_key_here"
}
}
}
}
Note:
npxauto-downloads the package on first run — no manual install needed. Ifuvisn't already on your machine, it will be installed automatically on first launch.Alternative: use
uvxdirectlyIf you already have
uvinstalled and prefer to skip the npm wrapper:{ "mcpServers": { "nativ": { "command": "uvx", "args": ["nativ-mcp"], "env": { "NATIV_API_KEY": "nativ_your_api_key_here" } } } }macOS tip: If you get
spawn uvx ENOENTin Cursor or Claude Desktop, GUI apps don't inherit your shell PATH. Use the full path (e.g."command": "/Users/you/.local/bin/uvx") or wrap in a login shell:"command": "/bin/sh", "args": ["-lc", "uvx nativ-mcp"].
Ask your AI assistant things like:
| Tool | Description |
|---|---|
translate | Translate text using the full localization engine (TM, style guides, brand voice, glossary) |
translate_batch | Translate multiple texts to a target language in one call |
search_translation_memory | Fuzzy-search the translation memory for existing translations |
add_translation_memory_entry | Add an approved translation to TM for future reuse |
get_languages | List all configured languages with formality and style settings |
get_translation_memory_stats | Get TM statistics — total entries, sources, and breakdown |
get_style_guides | List all style guides with their content and status |
get_brand_voice | Get the brand voice prompt that shapes all translations |
| URI | Description |
|---|---|
nativ://languages | Configured languages (JSON) |
nativ://style-guides | All style guides (JSON) |
nativ://brand-prompt | Brand voice prompt (JSON) |
nativ://tm/stats | Translation memory statistics (JSON) |
| Prompt | Description |
|---|---|
localize-content | Guided workflow to localize content into target languages |
review-translation | Review a translation against TM, style guides, and brand voice |
batch-localize-strings | Batch-localize i18n strings with structured output |
You: Translate "The future of luxury, delivered" to French and Japanese
AI: [calls translate tool for each language]
Translation (French): "L'avenir du luxe, livré chez vous"
TM Match: 0% — new translation, no prior TM entries
Rationale: "Livré chez vous" adds a personal touch absent from the literal
"livré", aligning with the brand's premium yet approachable voice.
Translation (Japanese): "ラグジュアリーの未来を、あなたの元へ"
TM Match: 45% partial — similar pattern found in TM from brand_voice source
You: Do we have translations for "Add to cart" in our TM?
AI: [calls search_translation_memory]
TM Search Results for "Add to cart" (3 matches):
- 95% [strong] "Add to cart" → "Ajouter au panier" (source: approved)
- 95% [strong] "Add to cart" → "In den Warenkorb" (source: brand_voice)
- 72% [partial] "Add items to cart" → "Ajouter des articles" (source: phrase_tm)
You: Localize these to French:
- "Sign up"
- "Log in"
- "Forgot password?"
- "Continue with Google"
AI: [calls translate_batch]
Batch translation to French (4 items):
1. "Sign up" → "S'inscrire" (TM 100%)
2. "Log in" → "Se connecter" (TM 100%)
3. "Forgot password?" → "Mot de passe oublié ?" (TM 92%)
4. "Continue with Google" → "Continuer avec Google" (TM 85%)
| Environment Variable | Required | Description |
|---|---|---|
NATIV_API_KEY | Yes | Your Nativ API key (nativ_xxx...) |
NATIV_API_URL | No | API base URL (defaults to https://api.usenativ.com) |
This MCP server acts as a bridge between your AI coding assistant and the Nativ API:
┌─────────────────────┐ ┌──────────────┐ ┌─────────────────┐
│ Claude / Cursor / │────▶│ Nativ MCP │────▶│ Nativ API │
│ Windsurf / etc. │◀────│ Server │◀────│ (Translation, │
│ │ │ (stdio) │ │ TM, Styles) │
└─────────────────────┘ └──────────────┘ └─────────────────┘
The MCP server runs locally via stdio. It authenticates with your API key and calls the Nativ REST API on your behalf. Your AI assistant sees Nativ's tools, resources, and prompts as native capabilities.
# Clone the repo
git clone https://github.com/nativ-ai/nativ-mcp.git
cd nativ-mcp
# Set up environment
uv venv
source .venv/bin/activate
uv pip install -e ".[dev]"
# Run the server (for testing)
NATIV_API_KEY=nativ_xxx nativ-mcp
# Run with MCP Inspector
NATIV_API_KEY=nativ_xxx npx @modelcontextprotocol/inspector uv run nativ-mcp
MIT — see LICENSE.
NATIV_API_KEY*secretYour Nativ API key (create at https://dashboard.usenativ.com → Settings → API Keys)
NATIV_API_URLOptional custom API URL (defaults to https://api.usenativ.com)
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent