TranslationX MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TranslationX MCP Server translate the file report.txt to Spanish"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TranslationX MCP Server (Python)
搭建Python虚拟环境
我们推荐通过uv构建虚拟环境来运行MCP server,关于`uv你可以在这里找到一些说明。
按照官方流程,你会安装Python包管理工具uv。除此之外,你也可以尝试其他方法(如Anaconda)来创建你的Python虚拟环境。
通过uv添加mcp依赖
uv add "mcp[cli]"验证mcp依赖是否安装成功,执行如下命令
uv run mcp当出现下图时代表安装成功

通过uv安装python,最低版本要求为3.13
uv python install 3.13获取 MCP Server
前往TranslationX Mcp Server 官方开源仓库下载
配置本地项目
通过uv创建一个项目
uv init mcp_server_translation将src文件夹拷贝到该目录下,通过如下命令测试mcp server是否正常运行
uv run --with mcp[cli] mcp run {YOUR_PATH}/src/main.py
# 如果是mac,需要加转义符
uv run --with mcp\[cli\] mcp run {YOUR_PATH}/src/main.py如果没有报错则MCP Server启动成功
在Cursor中使用
打开Cursor配置,在MCP中添加MCP Server

在文件中添加如下内容后保存, TRANSLATIONX_TOKEN 可以在X-DOC中获取
{
"mcpServers": {
"translationx": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"{YOUR_PATH}/src/main.py"
],
"env": {
"token": "<YOUR_TRANSLATIONX_TOKEN>"
}
}
}
}回到配置,此时TranslationX MCP Server已经启用

测试
创建项目,并创建文件夹,然后文件到文件夹中,并提交翻译:


Available Tools
22 toolsadd_memory_lib_entryC
给记忆库添加条目
Inputs: ml_id (required), source_text (required), target_text (required).
add_term_lib_entryC
添加术语库条目
Inputs: tl_id (required), source_text (required), target_text (required).
create_memory_libC
创建记忆库
Inputs: name (required), source_language (required), target_language (required).
create_projectD
创建项目
Inputs: project_name (required), project_no (required), comment.
create_project_folderD
创建项目文件夹
Inputs: id (required), name (required).
create_term_libC
创建术语库
Inputs: name (required), source_language (required), target_language (required).
delete_fileC
根据文件id删除文件
Inputs: ids (required).
delete_projectC
删除项目
Inputs: ids (required).
delete_project_fileC
删除项目文件
Inputs: project_id (required), ids (required), operation_type.
delete_project_folderC
删除项目文件夹
Inputs: id (required), folder_ids (required), operation_type.
download_target_fileB
根据文件id下载译文文件
Inputs: file_id (required), local_storage_path.
edit_projectC
编辑项目信息
Inputs: id (required), project_name (required), project_no (required), comment.
edit_project_folderC
编辑项目文件夹
Inputs: id (required), folder_id (required), name (required).
file_addC
文件翻译模块:上传文件
Inputs: file_path (required), file_name (required).
file_listC
根据用户提供的文件名称,获取文件的信息 根据状态筛选文件信息
Inputs: keyword, page, size, status.
get_language_codeB
获取语言code信息
Inputs: no named parameters.
get_memory_lib_listD
记忆库列表
Inputs: size, page, name.
get_project_folder_listC
获取项目文件夹列表
Inputs: id (required), status (required), keyword, page, +1 more.
get_project_listD
获取项目列表
Inputs: keyword, page, size.
get_term_lib_listD
术语库列表
Inputs: size, page, name.
submit_translationC
根据输入的参数提交翻译请求
传入需要提交翻译的文件id列表,源文件的语种和目标语种
语种对应的语种code为 {'世界语': 'eo', '中文(简体)': 'zh-cn', '丹麦语': 'da', '乌克兰语': 'uk', '乌兹别克语(拉丁)': 'uz', '乌尔都语': 'ur', '亚美尼亚语': 'hy', '伊博语': 'ig', '俄语': 'ru', '保加利亚语': 'bg', '信德语': 'sd', '修纳语': 'sn', '僧伽罗语': 'si', '克罗地亚语': 'hr', '克里奥语': 'kri', '冰岛语': 'is', '加利西亚语': 'gl', '加泰罗尼亚语': 'ca', '匈牙利语': 'hu', '南非荷兰语': 'af', '卡纳达语': 'kn', '卢森堡语': 'lb', '印地语': 'hi', '印度尼西亚语': 'id', '古吉拉特语': 'gu', '吉尔吉斯语(西里尔)': 'ky', '哈萨克语': 'kk', '土耳其语': 'tr', '塔吉克语': 'tg', '塞尔维亚语(拉丁)': 'sr-Latn', '塞尔维亚语(西里尔)': 'sr-Cyrl', '塞索托语': 'st', '夏威夷语': 'haw', '奥迪亚语': 'or', '威尔士语': 'cy', '孟加拉语': 'bn', '宿务语': 'ceb', '尼扬贾语': 'nya', '尼泊尔语': 'ne', '巴斯克语': 'eu', '巴西葡萄牙语': 'pt', '巽他语': 'su', '希伯来语': 'he', '希腊语': 'el', '库尔德语(中部)': 'ku', '库尔德语(北部)': 'kmr', '弗里西亚语': 'fy', '德语': 'de', '意大利语': 'it', '意第绪语': 'yi', '拉丁语': 'la', '拉脱维亚语': 'lv', '挪威语': 'nb', '捷克语': 'cs', '斯洛伐克语': 'sk', '斯洛文尼亚语': 'sl', '斯瓦希里语(拉丁)': 'sw', '旁遮普语': 'pa', '日文': 'ja', '普什图语': 'ps', '曼尼普尔语(美替隆语)': 'mni-Mtei', '未选择': '', '格鲁吉亚语': 'ka', '毛利语': 'mi', '法语': 'fr', '波兰语': 'pl', '波斯尼亚语(拉丁)': 'bs', '波斯语': 'fa', '泰卢固语': 'te', '泰米尔语': 'ta', '泰语': 'th', '海地克里奥尔语': 'ht', '爪哇语': 'jv', '爱尔兰语': 'ga', '爱沙尼亚语': 'et', '瑞典语': 'sv', '白俄罗斯语': 'be', '白苗语(拉丁)': 'mww', '祖鲁语': 'zu', '科萨语': 'xh', '科西嘉语': 'co', '立陶宛语': 'lt', '索马里语(阿拉伯)': 'so', '约鲁巴语': 'yo', '维吾尔语(阿拉伯)': 'ug', '缅甸语': 'my', '罗马尼亚语': 'ro', '老挝语': 'lo', '芬兰语': 'fi', '苏格兰盖尔语': 'gd', '英文': 'en', '荷兰语': 'nl', '菲律宾语': 'fil', '萨摩亚语(拉丁)': 'sm', '葡萄牙葡萄牙语': 'pt-pt', '蒙古语(传统)': 'mn-Mong', '蒙古语(西里尔)': 'mn-Cyrl', '西班牙语': 'es', '豪萨语': 'ha', '越南语': 'vi', '迪维希语': 'dv', '阿塞拜疆语(拉丁)': 'az', '阿姆哈拉语': 'am', '阿尔巴尼亚语': 'sq', '阿拉伯语': 'ar', '阿萨姆语': 'as', '韩语': 'ko', '马其顿语': 'mk', '马拉地语': 'mr', '马拉雅拉姆语': 'ml', '马来语(拉丁)': 'ms', '马耳他语': 'mt', '马达加斯加语': 'mg'}
可以选择要使用的术语库和记忆库
记忆库的格式为 {"memory_lib_id": 123, "threshold": 0.8}, memory_lib_id为记忆库ID,threshold为阈值
术语库的格式为 [123, 456, 789], 123为术语库ID
Inputs: file_ids (required), source_language (required), target_language (required), master_memory_libs, +1 more.
upload_project_fileC
上传项目文件
Inputs: file_path (required), file_name (required), project_id (required), folder_id (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Most tools have distinct purposes such as managing memory libraries, term libraries, projects, and files. However, there is potential confusion between 'delete_file' and 'delete_project_file', and between 'file_add' and 'upload_project_file', as their descriptions are brief and overlapping.
Tool names mix verb_noun patterns (e.g., 'create_memory_lib') with noun_verb patterns (e.g., 'file_add'), and some use different verbs for similar actions (e.g., 'edit_project' vs 'delete_project'). The naming is not fully consistent.
With 22 tools, the server covers core functionalities for a translation management system, including project, file, memory, and term library operations. The count is well-scoped and reasonable for the domain.
The tool set covers basic CRUD for projects and folders, file upload/download, and translation submission. However, it lacks update/delete for library entries, retrieval of single project details, and translation status checking, leaving notable gaps in the workflow.
Maintenance
Related MCP Connectors
MCP server for Translation Services
MCP server for Crowdin — projects, files, strings, translation progress, tasks, and members.
Accurate, brand-controlled translation for text, code, images, and documents with terminology.
Translate MCP — LibreTranslate-compatible machine translation.
Related MCP Servers
- AlicenseBqualityBmaintenanceAn MCP server providing machine translation capabilities via the Lara Translate API, featuring language detection and context-aware translations between numerous language pairs.22447 npm100MIT
- FlicenseNot gradedqualityDmaintenanceA ModelContextProtocol server providing high-quality translation services with a three-stage translation workflow (analysis, segmented translation, full-text review) that supports multiple languages and integrates with Claude and OpenAI-compatible models.26-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides DeepL translation capabilities, allowing AI assistants to translate text between supported languages via the DeepL API.3MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP (Multi-Agent Conversation Protocol) Server that enables AI agents to interact with Google's Cloud Translation API for translating text between languages.-