CAT
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Cross AI Tools

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Nativ

nativ-technologies/nativ-mcp
1authSTDIOregistry active
Summary

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.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Nativ MCP Server

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.

Smithery MCP Badge


Why use Nativ via MCP?

  • Translate in-context — localize strings, copy, and content directly from your editor without switching to a browser
  • Translation Memory aware — every translation checks your TM first, ensuring consistency across your project
  • Brand voice built-in — your team's tone, formality, and style guides are applied automatically
  • Review and approve — add approved translations to TM from your editor, building quality over time
  • Multi-format — JSON, CSV, Markdown, or freeform text — Nativ handles it all

Quick Start

1. Get a Nativ API Key

Sign up at dashboard.usenativ.com, go to Settings → API Keys, and create a key. It looks like nativ_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx.

2. Install

Add to your MCP configuration:

Claude Code / Claude Desktop (~/.claude/claude_desktop_config.json)

{
  "mcpServers": {
    "nativ": {
      "command": "npx",
      "args": ["-y", "nativ-mcp"],
      "env": {
        "NATIV_API_KEY": "nativ_your_api_key_here"
      }
    }
  }
}

Cursor (.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"
      }
    }
  }
}

Windsurf

{
  "mcpServers": {
    "nativ": {
      "command": "npx",
      "args": ["-y", "nativ-mcp"],
      "env": {
        "NATIV_API_KEY": "nativ_your_api_key_here"
      }
    }
  }
}

Note: npx auto-downloads the package on first run — no manual install needed. If uv isn't already on your machine, it will be installed automatically on first launch.

Alternative: use uvx directly

If you already have uv installed 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 ENOENT in 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"].

3. Use it

Ask your AI assistant things like:

  • "Translate 'Welcome back!' to French and German"
  • "Check our translation memory for existing translations of 'Sign up'"
  • "What are our style guides for localization?"
  • "Localize these i18n strings to all configured languages"
  • "Review this German translation against our TM and brand voice"

Tools

ToolDescription
translateTranslate text using the full localization engine (TM, style guides, brand voice, glossary)
translate_batchTranslate multiple texts to a target language in one call
search_translation_memoryFuzzy-search the translation memory for existing translations
add_translation_memory_entryAdd an approved translation to TM for future reuse
get_languagesList all configured languages with formality and style settings
get_translation_memory_statsGet TM statistics — total entries, sources, and breakdown
get_style_guidesList all style guides with their content and status
get_brand_voiceGet the brand voice prompt that shapes all translations

Resources

URIDescription
nativ://languagesConfigured languages (JSON)
nativ://style-guidesAll style guides (JSON)
nativ://brand-promptBrand voice prompt (JSON)
nativ://tm/statsTranslation memory statistics (JSON)

Prompts

PromptDescription
localize-contentGuided workflow to localize content into target languages
review-translationReview a translation against TM, style guides, and brand voice
batch-localize-stringsBatch-localize i18n strings with structured output

Examples

Translate a marketing headline

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

Check existing translations

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)

Batch localize i18n strings

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%)

Configuration

Environment VariableRequiredDescription
NATIV_API_KEYYesYour Nativ API key (nativ_xxx...)
NATIV_API_URLNoAPI base URL (defaults to https://api.usenativ.com)

How It Works

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.

Development

# 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

License

MIT — see LICENSE.

Links

  • Nativ Platform
  • Nativ Dashboard
  • MCP Protocol
  • Report Issues
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make money from your Skills
Make money from your Skills
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →

Configuration

NATIV_API_KEY*secret

Your Nativ API key (create at https://dashboard.usenativ.com → Settings → API Keys)

NATIV_API_URL

Optional custom API URL (defaults to https://api.usenativ.com)

Categories
AI & LLM Tools
Registryactive
Packagenativ-mcp
TransportSTDIO
AuthRequired
UpdatedFeb 19, 2026
View on GitHub

Related AI & LLM Tools MCP Servers

View all →
SkillFM LLM Cost Optimizer

io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage

LLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Llm Orchestration Agent

io.github.mikerawsonnz/llm-orchestration-agent

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith
Authenticated Llm Agent

io.github.mikerawsonnz/authenticated-llm-agent

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.
Copilot Memory MCP

labforgedev/copilot-memory-mcp

Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
1
Agent Prompt Injection Firewall Mcp

csoai-org/agent-prompt-injection-firewall-mcp

The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
Authenticated Multi Llm Agent

io.github.mikerawsonnz/authenticated-multi-llm-agent

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f