Devnagriai Translate Mcp

@devnagriai/devnagriai-translate-mcp

A JavaScript-based Model Context Protocol (MCP) server providing translation, language detection, and supported language listing via Devnagri AI APIs, with a focus on Indic languages.

Features

• Text Translation between 35+ languages (including all major Indic languages)
• Language Detection for any input text
• Supported Languages Listing
• MCP Protocol: Ready for AI tool integration
• Robust Error Handling and Validation
• Extensive Test Suite

Table of Contents

• [Features](#features)
• [Quick Start](#quick-start)
• [API Key Procurement](#api-key-procurement)
• [Installation](#installation)
• [NPX (Recommended)](#npx-recommended)
• [Manual Installation](#manual-installation)
• [Usage](#usage)
• [Direct Integration](#direct-integration)
• [Running the Server](#running-the-server)
• [MCP Tools](#mcp-tools)
• [Tool: translate](#tool-translate)
• [Tool: detectlanguage](#tool-detectlanguage)
• [Tool: listsupportedlanguages](#tool-listsupportedlanguages)
• [Configuration](#configuration)
• [Testing](#testing)
• [Contributing](#contributing)
• [Support](#support)
• [Security](#security)
• [License](#license)

Quick Start

npx @devnagriai/devnagriai-translate-mcp API_KEY="your_devnagri_api_key"

API Key Procurement

To use the Devnagri Translation API, you need an API key. Follow these steps:

1. Sign Up

• Go to Devnagri Dashboard and sign up for a free account.

1. Access API Hub

• After logging in, navigate to the API Hub section from the sidebar menu.

1. Select the Translation API

• Click on Get API Key.
• Click Create.
• Enter a name for the API key.
• Click Save.

1. Copy API Key

• Copy the generated API key. Keep it secure and do not share it publicly.

Installation

NPX (Recommended)

The simplest way to use this MCP server is through npx, which allows you to run it without installing:

npx @devnagriai/devnagriai-translate-mcp API_KEY="your_devnagri_api_key"

This is ideal for integration with AI tools like Claude, GPT, Windsurf, and Cursor.

Manual Installation

If you prefer to install the server locally:

1. Clone the repository:

git clone https://github.com/DevnagriAI/devnagriai-translate-mcp.git
cd devnagriai-translate-mcp

1. Install dependencies:

npm install

1. Set up environment variables:

Create a .env file in the root directory with the following content:

DEVNAGRI_API_KEY=your_devnagri_api_key

Usage

Direct Integration

For local/private use or development, add the server to your MCP config:

{
  "mcpServers": {
    "devnagri-translation": {
      "command": "npx",
      "args": [
        "@devnagriai/devnagriai-translate-mcp",
        "API_KEY=\"your_devnagri_api_key\""
      ]
    }
  }
}

Running the Server

Start the server:

npm start

For development with auto-reload:

npm run dev

This MCP server can be used with any MCP client. For example, using the MCP CLI client:

mcp-client --transport stdio -- node src/index.js

Integration with AI Tools

Windsurf

In ~/.codeium/windsurf/mcp_config.json:

{
  "devnagri-translation": {
    "command": "npx",
    "args": [
      "@devnagriai/devnagriai-translate-mcp",
      "API_KEY=\"your_devnagri_api_key\""
    ]
  }
}

Cursor

In Cursor's settings:

{
  "tools": {
    "devnagri-translation": {
      "command": "npx",
      "args": [
        "@devnagriai/devnagriai-translate-mcp",
        "API_KEY=\"your_devnagri_api_key\""
      ],
      "transport": "stdio"
    }
  }
}

Claude

In Claude Desktop App:

1. Go to Settings > Extensions
2. Click "Add Custom Extension"
3. Select "Add from local server"
4. Enter the following details:

• Name: Devnagri Translation Service
• Command: npx @devnagriai/devnagriai-translate-mcp API_KEY="your_devnagri_api_key"
• Transport: stdio

Or use this configuration:

{
  "devnagri-translation": {
    "command": "npx",
    "args": [
      "@devnagriai/devnagriai-translate-mcp",
      "API_KEY=\"your_devnagri_api_key\""
    ],
    "transport": "stdio"
  }
}

MCP Tools

The following tools are exposed via this MCP server:

| Tool Name | Description | |--------------------------|---------------------------------------------| | translate | Translate text between supported languages | | detect_language | Detect the language of given text | | list_supported_languages | List all available languages |

Refer to examples/mcp_config_example.json for sample tool configuration.

Tool: translate

Translates text from source language to target language.

Parameters:

• source_text (string, required): The text to be translated
• source_language (string, required): The source language code (e.g., "en")
• target_language (string, required): The target language code (e.g., "hi")
• translation_type (string, optional): Type of translation requested ("literal" or "base", defaults to "literal")

Returns:

{
  "translated_text": "नमस्ते, आप कैसे हैं?",
  "source_language": "en",
  "target_language": "hi",
  "translation_type": "literal"
}

Tool: detect_language

Detects the language of the provided text.

Parameters:

• text (string, required): The text for language detection

Returns:

{
  "detected_language": "en",
  "confidence_score": 0.98,
  "supported": true
}

Tool: listsupportedlanguages

Returns a list of all supported languages for translation.

Parameters:

• None

Returns:

[
  {
    "name": "English",
    "native_name": "English",
    "code": "en"
  },
  {
    "name": "Hindi",
    "native_name": "हिन्दी",
    "code": "hi"
  },
  // ... more languages
]

Configuration

• API Key: Required. Pass as an environment variable or command-line argument: API_KEY="your_devnagri_api_key"
• Port: Defaults to 8080 (can be configured via MCP protocol parameters)
• .env Support: You may place your API key in a .env file for local development.

Testing

Run the test suite with:

npm test

Test coverage includes unit and integration tests for all MCP tools and API client logic.

Contributing

1. Fork the repository
2. Create a feature branch
3. Submit a pull request describing your changes

Support

• For API issues, contact Devnagri Support
• For MCP server issues, open a GitHub issue in this repository

Security

• Never share your API key publicly
• Rotate API keys periodically via the Devnagri dashboard

License

MIT

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: DevnagriAI
• Source: DevnagriAI/devnagriai-translate-mcp
• License: MIT
• Homepage: https://devnagri.com

Install and usage instructions live in the source repository linked above.