
Polyglot
An MCP server that provides standardized translation services across six languages (Arabic, Chinese, English, French, Russian, Spanish) using Claude Sonnet 3.5, with support for different domains and formality levels.
README
Polyglot - Model Contexts Protocol for Translation
Polyglot is an open-source implementation of the Model Contexts Protocol (MCP) focused on translation services. It provides a standardized way to handle translation requests across multiple languages using Claude Sonnet 3.5.
Supported Languages
- Arabic (ar)
- Chinese (zh)
- English (en)
- French (fr)
- Russian (ru)
- Spanish (es)
Features
- Standardized translation request format
- Support for multiple domains (legal, medical, general)
- Formality level control (formal/informal)
- Claude Sonnet 3.5 integration
- MCP protocol server (via FastMCP)
- API key authentication
Installation
Using uv (Recommended)
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Install the package and its dependencies
uv pip install .
# For development, install with dev dependencies
uv pip install ".[dev]"
Using pip
# Install the package and its dependencies
pip install .
# For development, install with dev dependencies
pip install ".[dev]"
Configuration
- Create a
.env
file in your project root:
ANTHROPIC_API_KEY=your_api_key_here
- Make sure to keep your API key secure and never commit it to version control.
Running the MCP Server
The Polyglot MCP server uses FastMCP to expose translation tools and resources over the MCP protocol (SSE transport).
To start the server:
python -m polyglot.server
By default, the server will run on port 8001 using SSE transport.
Testing the MCP Server
Using MCP Inspector (Recommended)
- Install the MCP Inspector:
npx @modelcontextprotocol/inspector
- Open the Inspector UI (the terminal will show a local address).
- Set the following in the Inspector UI:
- Transport Type: SSE
- URL:
http://localhost:8001/sse
- (Optional) Set Inspector Proxy Address if needed
- You can now interact with the translation tool and resources via the Inspector UI.
Using a Python MCP Client
You can also interact with the server programmatically using the MCP Python SDK:
from mcp.client.sse import sse_client
import asyncio
async def main():
async with sse_client(url="http://localhost:8001/sse") as (read, write):
# Example: call the translate tool
request = {
"tool": "translate",
"args": {
"request": {
"version": "1.0",
"type": "translation_request",
"metadata": {
"source_language": "fr",
"target_language": "en",
"domain": "legal",
"formality": "formal",
"api_key": "your_api_key_here" # Required for authentication
},
"data": {"text": "Le contrat a été signé hier à Genève."}
}
}
}
await write(request)
response = await read()
print(response)
asyncio.run(main())
Protocol Specification
The translation request follows this JSON structure:
{
"version": "1.0",
"type": "translation_request",
"metadata": {
"source_language": "fr",
"target_language": "en",
"domain": "legal",
"formality": "formal",
"api_key": "your_api_key_here" // Required for authentication
},
"data": {
"text": "Le contrat a été signé hier à Genève."
}
}
Development
To set up the development environment:
# Install uv if you haven't already
curl -LsSf https://astral.sh/uv/install.sh | sh
# Create and activate a virtual environment
uv venv
source .venv/bin/activate # On Unix/macOS
# or
.venv\Scripts\activate # On Windows
# Install development dependencies
uv pip install ".[dev]"
License
MIT License
推荐服务器

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。
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。
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。
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。

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。
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。
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。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。