Lingo.dev (Translation) MCP server

Lingo.dev is an AI-powered open-source CLI tool for web and mobile app localization, designed to produce authentic translations instantly. It eliminates manual work and management overhead, allowing teams to perform accurate localization much faster and ship features to global users. You can use it with your own LLM or with Lingo.dev's managed Localization Engine.

Getting Started

Using Your Own LLM

1. Create an i18n.json configuration file:

{
  "version": 1.5,
  "provider": {
    "id": "anthropic",
    "model": "claude-3-7-sonnet-latest",
    "prompt": "You're translating text from {source} to {target}."
  },
  "locale": {
    "source": "en",
    "targets": ["es", "fr", "de"]
  }
}

2. Set your API key as an environment variable:

export ANTHROPIC_API_KEY=your_anthropic_api_key
# or for OpenAI
export OPENAI_API_KEY=your_openai_api_key

3. Run the localization:

npx lingo.dev@latest i18n

Using Lingo.dev Cloud

For production-grade applications requiring features like translation memory, glossary support, and quality assurance:

1. Create a simplified i18n.json configuration file:

{
  "version": 1.5,
  "locale": {
    "source": "en",
    "targets": ["es", "fr", "de"]
  }
}

2. Authenticate with Lingo.dev:

npx lingo.dev@latest auth --login

3. Run localization:

npx lingo.dev@latest i18n

Caching with i18n.lock

Lingo.dev uses an i18n.lock file to track content checksums, ensuring only changed text gets translated. This provides:

• Speed: Skip already translated content
• Consistency: Prevent unnecessary retranslations
• Cost efficiency: No billing for repeated translations

GitHub Action Integration

Integrate Lingo.dev into your CI/CD pipeline with the GitHub Action:

- uses: lingodotdev/lingo.dev@main
  with:
    api-key: ${{ secrets.LINGODOTDEV_API_KEY }}

This action runs lingo.dev i18n on every push, keeping your translations up-to-date automatically.

For more configuration options, visit the GitHub Action documentation.

Key Features

• Instant integration: Works with your codebase in minutes
• CI/CD Automation: Set it and forget it
• Global reach: Ship to users everywhere
• AI-powered: Uses latest language models for natural translations
• Format-agnostic: JSON, YAML, CSV, Markdown, Android, iOS, and many more
• Clean diffs: Preserves your file structure exactly
• Lightning-fast: Translations in seconds, not days
• Always synced: Automatically updates when content changes
• Human quality: Translations that don't sound robotic

Additional Resources

For detailed guides and API references, visit the Lingo.dev documentation.

How to add this MCP server to 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 > MCP and click "Add new global MCP server".

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

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

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 explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.