angular-i18n-mcp

angular-i18n-mcp

Manages Angular internationalization (i18n) by extracting, listing, and updating translation strings in XLIFF format through MCP tools.

Category
访问服务器

README

Angular i18n MCP Server

This MCP server provides tools to manage Angular internationalization (i18n) using XLIFF 1.2 and 2.0 formats. It integrates with ng-extract-i18n-merge to automate the extraction and merging of translation strings.

Why use this MCP server?

Managing translation files (XLIFF) in Angular projects can be challenging for AI models due to the size and complexity of the XML files. This MCP server solves this by:

  • LLM-Friendly Interface: Provides concise JSON output for translation units, avoiding the need for AI to parse large XML files.
  • Accurate Extraction: Leverages the Angular CLI to extract strings directly from source code, ensuring all i18n attributes are captured.
  • Structured Updates: Automatically handles XML serialization and ensures proper escaping of special characters, maintaining the integrity of your translation files.
  • Efficient Workflow: Supports listing only new translations and performing bulk updates, making the localization process faster and more reliable.

Features

  • Extract i18n: Runs the Angular CLI command to extract strings and merge them into target locale files.
  • List New Translations: Identifies units that are newly added and haven't been translated yet (marked with state="initial").
  • List All Translations: Provides a paginated list of all translation units.
  • Update Translations: Updates multiple translation units in a single call.
  • I18N Settings: Retrieves the i18n configuration from angular.json.

Prerequisites

  • Node.js installed.
  • An Angular project configured for i18n as described in the Angular i18n Guide.
  • The project should be configured with ng-extract-i18n-merge:
    ng add ng-extract-i18n-merge
    
  • Angular configuration (angular.json) should define the target locales and the translation format (xlf or xlf2).

Configuration

While this is a standard MCP server that works with any MCP-compatible client, the following configuration example is specifically for the Gemini CLI.

The server requires configuration in .gemini/settings.json. You can place this file in either:

  • Your user home directory: ~/.gemini/settings.json
  • The project root directory: ./.gemini/settings.json

Add the following to your configuration:

{
  "mcpServers": {
    "angular-i18n": {
      "command": "npx",
      "args": ["-y", "angular-i18n-mcp"],
      "env": {
        "LOCALE_DIR": "src/locale"
      }
    }
  }
}

Environment Variables:

  • LOCALE_DIR: (Optional) The directory where translation files are stored. Defaults to src/locale.

It is recommended to add src/locale to your .geminiignore file to prevent Gemini from reading large translation files directly or attempting manual updates.

It is strongly recommended to use I18N metadata for translation to provide additional context for translators. This will allow the AI to provide better suggestions and translations.

Tools

extract_i18n

  • Extracts strings from the source code and merges them into the .xlf files.

get_i18n_settings

  • Retrieves the i18n section from angular.json to identify configured locales and source language.

list_new_translations

  • Lists newly added translation units that haven't been translated yet (marked with state="initial").
  • Arguments:
    • locale: The target language code (e.g., de).
    • page (optional): Page number for pagination.
    • pageSize (optional): Number of units per page.

list_all_translations

  • Lists all translation units in a locale file.
  • Arguments:
    • locale: The target language code.
    • page (optional): Page number.
    • pageSize (optional): Number of units per page.

update_translations

  • Updates multiple translation units (up to 50) in a single call. Sets the state to translated.
  • Arguments:
    • locale: The target language code.
    • updates: An array of objects, each containing id and translation.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选