Nativ

io.github.Nativ-Technologies由 GitHub 账号 Nativ-Technologies 发布v0.1.3更新于 Oct 24, 2026

AI-powered localization — translate, manage translation memory, and access style guides.

概览

AI 生成的概览

让助手借助 Nativ 的翻译记忆库、术语表和品牌语调,翻译并本地化文本、图片、音频和字幕。

可以做什么
把 AI 助手连接到 Nativ 本地化平台。工具包括 translate 与 translate_batch、翻译记忆库的模糊搜索与条目添加、语言、风格指南和品牌语调查询,以及图片文字识别与就地图片本地化、文化适配检查、音频转写与 TTS 配音、字幕本地化。还提供语言、风格指南、品牌提示和翻译记忆库统计等资源,以及本地化和审校内容的引导提示。
适用场景
适合在编辑器中本地化产品文案、营销内容或 i18n 文件,或在发布本地化内容前核对已有译文与风格规范。也适用于图片文字、字幕和配音的本地化。
运行要求
以 stdio 在本地运行,通常通过 npx nativ-mcp 或 uvx nativ-mcp 启动,因此需要 Node.js 或 uv。需要 Nativ 账号和 NATIV_API_KEY 环境变量,NATIV_API_URL 为可选。需要访问 Nativ API 的网络连接。
安装前请注意
NATIV_API_KEY 是发送给 Nativ API 的密钥,提交翻译的内容会离开本机。部分工具会写入平台:add_translation_memory_entry 会添加已批准的译文,synthesize_audio 会产生计费。图片、音频和视频工具会读取本地文件并把结果写入磁盘。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Nativ,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

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

For a remote Streamable HTTP connection, see Hosted MCP. Hosted calls use your API key in X-API-Key; the stdio setup below uses NATIV_API_KEY in the environment. JSON-only API clients can import the tools schema and call /tools/{tool_name} with HTTPS media URLs.

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

json
{  "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
extract_image_textExtract on-image text segments (OCR) in reading order
localize_imageReplace on-image text with translations in place, keeping layout and graphics intact
check_image_cultural_fitFlag cultural-sensitivity issues in an image across target markets
transcribe_audioSpeech-to-text for a local audio or video file (draft; billed on synthesize)
parse_audio_scriptParse a script (.txt/.docx/.pdf/.srt) instead of running STT
list_voicesList TTS voices for dubbing
preview_voiceSave a short TTS preview WAV to disk
get_voice_consent_scriptConsent copy required for voice cloning
synthesize_audioGenerate billed localized TTS (and optional dubbed MP4) and save to disk
register_videoStore a source video for later remux
remux_videoMux a WAV onto a registered video
parse_subtitleParse a local SRT/ITT into timed cues
localize_subtitlesLocalize subtitles in-memory from SRT/ITT and/or video STT

| clone_voice | Create a Google voice clone from reference speech and spoken consent | | create_byo_voice | Create and save an original-speaker clone from audio/video, or a Google clone with consent | | delete_saved_voice | Delete a saved cloned voice when requested | | get_audio_capabilities | Read account media duration limits and long-form eligibility | | transcribe_audio_detailed | Return complete transcript segments, speaker IDs, timings and media IDs | | translate_dialogue | Translate related speaker turns together, with timing and review details | | synthesize_audio_advanced | Dub with speaker-specific voices, music, timing and complete review data | | upload_subtitle | Save an SRT/ITT source, with optional auto-localization | | list_subtitles | List saved subtitle sources and localized files | | localize_subtitle_file | Localize an already saved ITT source | | get_subtitle_download_url | Get an expiring download URL for a saved subtitle | | delete_subtitle | Delete a saved subtitle when requested | | get_subtitle_review | Read subtitle QC rows and approval status | | update_subtitle_review | Save reviewed subtitle translations and approvals | | export_subtitle | Export subtitles with review edits, or a QC workbook | | list_translation_memory_entries | List and paginate TM entries with IDs | | update_translation_memory_entry | Edit or enable/disable an existing TM entry | | delete_translation_memory_entry | Delete a TM entry when requested | | list_language_settings | Get complete language settings with IDs for updates | | get_language_formality_options | List supported formality settings | | update_language_formality | Save a workspace language's formality | | update_language_custom_style | Save or clear per-language style instructions | | list_style_guides | Get complete style-guide content and IDs for editing | | get_combined_prompt | Read the combined brand prompt and enabled style guides | | create_style_guide | Create a workspace style guide | | update_style_guide | Edit or enable/disable an existing style guide | | delete_style_guide | Delete a style guide when requested | | upload_style_guide | Import a style guide from .txt or .docx | | reorder_style_guides | Save the order of style guides | | submit_translation_feedback | Save feedback or an approval rating |

All 51 tools are shared by local and hosted MCP. Existing tools retain their arguments and results. Voice cloning uses the existing API and requires the user’s ownership/permission confirmation. See the workflow coverage audit for original-voice dubbing and saved-subtitle examples.

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

bash
# Clone the repogit clone https://github.com/nativ-ai/nativ-mcp.gitcd nativ-mcp
# Set up environmentuv venvsource .venv/bin/activateuv pip install -e .
# Run the server (for testing)NATIV_API_KEY=nativ_xxx nativ-mcp
# Run with MCP InspectorNATIV_API_KEY=nativ_xxx npx @modelcontextprotocol/inspector uv run nativ-mcp

License

MIT — see LICENSE.

Links

来源:README.md,提交 5639338

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v0.1.3最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分