What do I need to set up the Nativ MCP server?
You need a Nativ API key from the Nativ dashboard (Settings → API Keys). Set it as the `NATIV_API_KEY` environment variable.

@Nativ-Technologies
基本信息
AI-powered localization platform. Translate text, search translation memory, and access style guides from any MCP-compatible AI tool.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"nativ": {
"command": "uvx",
"args": [
"nativ-mcp"
],
"env": {
"NATIV_API_KEY": "<YOUR_NATIV_API_KEY>"
}
}
}
}Translate text using the full localization engine (TM, style guides, brand voice, glossary)
Translate multiple texts to a target language in one call
Fuzzy-search the translation memory for existing translations
Add an approved translation to TM for future reuse
List all configured languages with formality and style settings
Get TM statistics — total entries, sources, and breakdown
List all style guides with their content and status
Get the brand voice prompt that shapes all translations
Nativ is an MCP server that brings AI-powered localization into MCP-compatible tools like Claude Code, Cursor, and Windsurf. It translates content while respecting a team's brand voice, translation memory, glossaries, and style guides.
Get a Nativ API key from the Nativ dashboard, add the server to your MCP configuration with npx -y nativ-mcp and the NATIV_API_KEY environment variable, then ask your AI assistant to translate text, search translation memory, or localize strings.
You need a Nativ API key from the Nativ dashboard (Settings → API Keys). Set it as the `NATIV_API_KEY` environment variable.
It runs locally via stdio, authenticating with your API key and calling the Nativ REST API on behalf of your AI assistant.
Nativ supports JSON, CSV, Markdown, and freeform text.
Yes, if you have uv installed, you can use `uvx nativ-mcp` instead of `npx -y nativ-mcp`.
It provides eight tools: `translate`, `translate_batch`, `search_translation_memory`, `add_translation_memory_entry`, `get_languages`, `get_translation_memory_stats`, `get_style_guides`, and `get_brand_voice`.

Model Context Protocol Servers
Painless E2E Automation for Mobile and Web

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.
Open-source MCP to use Blender with any LLM
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
评论