
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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.