AiryLark Translation MCP server for AI agents

AiryLark MCP server is a specialized translation service module that follows the Model Context Protocol (MCP), enabling AI assistants like Claude to access professional-grade translation capabilities through a standardized interface. It offers high-precision translations with advanced features like domain-specific terminology recognition and quality assessment.

Installation Requirements

Prerequisites

Node.js (v18+) and npm

Setup Instructions

Install dependencies:

cd mcp-server
npm install

Configure environment variables by creating a .env file with the following settings:

# Translation API Configuration
TRANSLATION_API_KEY=your_api_key
TRANSLATION_MODEL=your_model_name
TRANSLATION_BASE_URL=your_api_base_url

# Server Configuration
PORT=3031  # MCP server port, optional, defaults to 3031

Running the Server

Development Environment

Start the development server with:

npm run dev

Production Environment

Build and start the server:

npm run build
npm start

Docker Deployment

Using Docker

# Pull the official image
docker pull wizdy/airylark-mcp-server

# Run the container
docker run -p 3031:3031 --env-file .env -d wizdy/airylark-mcp-server

Using Docker Compose

Create a docker-compose.yml file:

services:
  mcp-server:
    image: wizdy/airylark-mcp-server
    ports:
      - "${MCP_PORT}:${MCP_PORT}"
    environment:
      - NODE_ENV=production
      - PORT=${MCP_PORT}
      - TRANSLATION_API_KEY=${TRANSLATION_API_KEY}
      - TRANSLATION_MODEL=${TRANSLATION_MODEL}
      - TRANSLATION_BASE_URL=${TRANSLATION_BASE_URL}
    restart: always

Then run:

# Set environment variables or create .env file
export MCP_PORT=3031
export TRANSLATION_API_KEY=your_api_key
export TRANSLATION_MODEL=your_model_name
export TRANSLATION_BASE_URL=your_api_base_url

# Start the service
docker-compose up -d

Available MCP Tools

1. Text Translation Tool (translate_text)

Provides professional-grade text translation that automatically adapts to different domains and styles.

Parameters:

text: Source text to translate
target_language: Target language code (e.g., 'zh', 'en', 'ja')
source_language: (Optional) Source language code
high_quality: (Optional) Whether to enable high-precision translation process, defaults to true

Usage Scenarios:

Set high_quality=true for professional documents, academic papers, etc.
Set high_quality=false for informal content or quick translations

2. Translation Quality Assessment Tool (evaluate_translation)

Evaluates translation quality and provides detailed feedback.

Parameters:

original_text: Original text
translated_text: Translated text
detailed_feedback: (Optional) Whether to provide detailed feedback, defaults to false

Evaluation Metrics:

Accuracy: Does the translation accurately convey the original meaning
Fluency: Does the translation conform to target language expression habits
Terminology: Accuracy and consistency of professional terminology translation
Style consistency: Whether the translation maintains the style of the original text

Integration with AI Assistants

Programmatic Integration

import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { SSEClientTransport } from "@modelcontextprotocol/sdk/client/sse.js";

// Connect to the MCP server
const transport = new SSEClientTransport("http://localhost:3031");
const client = new Client(
  { name: "assistant-client", version: "1.0.0" },
  { capabilities: { tools: {} } }
);
await client.connect(transport);

// Call the professional translation tool
const result = await client.callTool({
  name: "translate_text",
  arguments: {
    text: "The mitochondrion is the powerhouse of the cell.",
    target_language: "zh",
    high_quality: true
  }
});

console.log(result.content[0].text);

Cursor Configuration

Add the following MCP server configuration in Cursor settings:

{
  "mcpServers": {
    "airylark-translation": {
      "url": "https://airylark-mcp.vcorp.ai/sse"
    }
  }
}

Claude Chat Configuration

To enable MCP server connection in Claude Chat:

Go to settings page
Find "Developer Settings" or "External Tools" option
Add a new MCP server, enter name and URL
Server URL: https://airylark-mcp.vcorp.ai/sse

Translation Features and Advantages

Three-stage translation process: Analysis and planning, segmented translation, and full-text review to ensure quality for professional domain documents
Domain terminology recognition: Automatically identifies professional text domains, extracts key terms, and ensures terminology consistency
Quality assessment system: Provides comprehensive translation quality assessment
Multi-language support: Supports translation between Chinese, English, Japanese, Korean, French, German, and more
Style and format preservation: Automatically adjusts translation style based on text type

Use Cases

Technical documentation translation
Academic paper translation
Legal document translation
Medical information translation
Financial report translation

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "airylark-translation" '{"url":"https://airylark-mcp.vcorp.ai/sse"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "airylark-translation": {
            "url": "https://airylark-mcp.vcorp.ai/sse"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

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

2. Add this to your configuration file:

{
    "mcpServers": {
        "airylark-translation": {
            "url": "https://airylark-mcp.vcorp.ai/sse"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect