texterify-mcp

texterify-mcp

An MCP server that provides LLM agents with full access to the Texterify translation management API. It enables users to search, create, update, and delete translation keys and their values directly through natural language within their development environment.

Category
访问服务器

README

texterify-mcp

npm version License: ISC

A Model Context Protocol (MCP) server that gives LLM agents full access to the Texterify translation management API. Search, create, update, and delete translation keys and their translations without leaving your editor.

Why

Managing translations during development means constant context-switching between your code editor and the Texterify web UI. This MCP server eliminates that friction -- your AI coding assistant can look up keys, add translations, find untranslated strings, and manage languages directly through natural language.

Quick Start

The fastest way to get started is via npx:

npx texterify-mcp

Or install globally:

npm install -g texterify-mcp

The server requires the following environment variables:

Variable Required Description
TEXTERIFY_AUTH_EMAIL Yes Your Texterify account email
TEXTERIFY_AUTH_SECRET Yes Your Texterify API secret / access token
TEXTERIFY_PROJECT_ID No UUID of the project to operate on (can be provided per-tool or via env)
TEXTERIFY_API_BASE_URL No API base URL (default: https://app.texterify.com/api)
TEXTERIFY_API_VERSION No API version (default: v1)

You can find your API credentials in your Texterify account settings.

Note on TEXTERIFY_PROJECT_ID: While this can be set as an environment variable for convenience, every project-scoped tool also accepts an optional project_id parameter. The resolution order is: tool parameter → environment variable → error. You can find your project ID in your project's texterify.json file or by using the list_projects tool.

Client Configuration

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "texterify": {
      "command": "npx",
      "args": ["-y", "texterify-mcp"],
      "env": {
        "TEXTERIFY_AUTH_EMAIL": "you@example.com",
        "TEXTERIFY_AUTH_SECRET": "your-api-secret",
        "TEXTERIFY_PROJECT_ID": "your-project-uuid"
      }
    }
  }
}

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %AppData%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Claude Code

claude mcp add --transport stdio \
  --env TEXTERIFY_AUTH_EMAIL=you@example.com \
  --env TEXTERIFY_AUTH_SECRET=your-api-secret \
  --env TEXTERIFY_PROJECT_ID=your-project-uuid \
  texterify -- npx -y texterify-mcp

Note: All flags (--transport, --env) must come before the server name. The -- separates the server name from the command. TEXTERIFY_PROJECT_ID is optional and can be provided per-tool.

OpenCode

Add to your opencode.json (or opencode.jsonc):

{
  "mcp": {
    "texterify": {
      "type": "local",
      "command": ["npx", "-y", "texterify-mcp"],
      "environment": {
        "TEXTERIFY_AUTH_EMAIL": "you@example.com",
        "TEXTERIFY_AUTH_SECRET": "your-api-secret",
        "TEXTERIFY_PROJECT_ID": "your-project-uuid"
      }
    }
  }
}

TEXTERIFY_PROJECT_ID is optional and can be provided per-tool.

VS Code / Copilot

Add to .vscode/mcp.json in your workspace (or add to your user profile via MCP: Add Server in the Command Palette):

{
  "servers": {
    "texterify": {
      "command": "npx",
      "args": ["-y", "texterify-mcp"],
      "env": {
        "TEXTERIFY_AUTH_EMAIL": "you@example.com",
        "TEXTERIFY_AUTH_SECRET": "your-api-secret",
        "TEXTERIFY_PROJECT_ID": "your-project-uuid"
      }
    }
  }
}

TEXTERIFY_PROJECT_ID is optional and can be provided per-tool.

Cursor

Add to .cursor/mcp.json in your project root (project-specific) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "texterify": {
      "command": "npx",
      "args": ["-y", "texterify-mcp"],
      "env": {
        "TEXTERIFY_AUTH_EMAIL": "you@example.com",
        "TEXTERIFY_AUTH_SECRET": "your-api-secret",
        "TEXTERIFY_PROJECT_ID": "your-project-uuid"
      }
    }
  }
}

TEXTERIFY_PROJECT_ID is optional and can be provided per-tool.

Available Tools

list_keys

Search and list translation keys with pagination. Supports filtering by name and untranslated status.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
search string No Filter keys by name
only_untranslated boolean No Return only untranslated keys
page number No Page number (default: 1)
per_page number No Results per page (default: 10, max: 50)

get_key

Retrieve a single translation key with all its translations.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
key_id string Yes UUID of the key

create_key

Create a new translation key.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
name string Yes Key name (e.g. welcome_message)
description string No Human-readable description
html_enabled boolean No Allow HTML in value
pluralization_enabled boolean No Enable pluralization

update_key

Update an existing key's properties. Only provided fields are changed.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
key_id string Yes UUID of the key
name string No New key name
description string No New description
html_enabled boolean No Toggle HTML support
pluralization_enabled boolean No Toggle pluralization

delete_keys

Delete one or more translation keys.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
key_ids string[] Yes Array of key UUIDs to delete

set_translation

Create or update a translation for a specific key and language (upsert).

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
key_id string Yes UUID of the key
language_id string Yes UUID of the language
content string Yes Translation text
zero string No Plural form: zero
one string No Plural form: one
two string No Plural form: two
few string No Plural form: few
many string No Plural form: many

list_languages

List languages configured in the project with translation progress.

Parameter Type Required Description
project_id string No The Texterify project UUID. If omitted, uses TEXTERIFY_PROJECT_ID env var
search string No Filter by language name
page number No Page number (default: 1)
per_page number No Results per page (default: 10, max: 50)

list_projects

List all Texterify projects accessible to the authenticated user. Useful for finding project IDs.

Parameter Type Required Description
search string No Filter by project name
page number No Page number (default: 1)
per_page number No Results per page (default: 10, max: 50)

Example Prompts

Once configured, you can ask your AI assistant things like:

  • "List all untranslated keys in my project"
  • "Create a key called checkout.success_message with description 'Shown after payment'"
  • "What languages are configured in this project?"
  • "Set the German translation for key X to 'Willkommen'"
  • "Find all keys matching 'error'"
  • "Delete the keys I just created"

Development

Requires Node.js 18+ and pnpm.

# Install dependencies
pnpm install

# Run the server
pnpm start

# Run in watch mode
pnpm dev

# Type-check
pnpm exec tsc --noEmit

# Run tests
pnpm test

How It Works

The server uses stdio transport -- it communicates over stdin/stdout using the MCP JSON-RPC protocol. All logging goes to stderr to keep the protocol channel clean.

MCP Client (LLM Agent)
    |  stdio (JSON-RPC)
    v
Tool Handlers (Zod-validated inputs)
    |
    v
API Client (native fetch)
    |
    v
Texterify REST API
  • No build step -- TypeScript is executed directly via tsx
  • Native fetch -- zero HTTP library dependencies (Node.js 18+)
  • Zod v4 schemas for input validation and automatic JSON Schema generation
  • Structured error handling with clear messages for auth failures, missing resources, and validation errors

License

ISC

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