Weblate MCP Server
MCP server for managing translation projects in Weblate. With the ability to search, read and write transltaions.
Tools
listProjects
List all available Weblate projects
listComponents
List components in a specific project
listLanguages
List languages available in a specific project
searchStringInProject
Search for translations containing specific text in a project
getTranslationForKey
Get translation value for a specific key in a project
writeTranslation
Update or write a translation value for a specific key
searchTranslationsByKey
Search for translations by key pattern across components in a project
findTranslationsForKey
Find all translations for a specific key across all components and languages in a project
listTranslationKeys
List all translation keys in a project (optionally filtered by component)
searchTranslationKeys
Search for translation keys by pattern in a project
README
Weblate MCP Server
A Model Context Protocol (MCP) server that provides seamless integration with Weblate translation management platform. This server enables AI assistants to interact directly with your Weblate instance for comprehensive translation management.
🌟 Features
- 🔧 Complete Weblate API Access: Full integration with Weblate's REST API
- 🤖 AI-Powered Workflow: Natural language interaction with your translation projects
- 📊 Project Management: Create, list, and manage translation projects
- 🔍 Component Operations: Handle translation components and configurations
- ✏️ Translation Management: Update, search, and manage translations
- 🌐 Language Support: Work with all supported languages in your Weblate instance
- 🚀 Multiple Transports: HTTP/SSE, Streamable HTTP, and STDIO support
- 🛡️ Type Safety: Full TypeScript implementation with comprehensive error handling
🎯 What is This?
This MCP server acts as a bridge between AI assistants (like Claude Desktop) and your Weblate translation management platform. Instead of manually navigating the Weblate web interface, you can use natural language to:
- "List all projects in my Weblate instance"
- "Show me the French translations for the frontend component"
- "Update the welcome message translation"
- "Create a new translation project"
🚀 Quick Start
Option 1: Use with npx (Recommended)
The easiest way to use this MCP server is with npx - no installation required!
For Claude Desktop or other MCP clients:
{
"mcpServers": {
"weblate": {
"command": "npx",
"args": ["-y", "@mmntm/weblate-mcp"],
"env": {
"WEBLATE_API_URL": "https://your-weblate-instance.com/api",
"WEBLATE_API_TOKEN": "your-weblate-api-token"
}
}
}
}
Manual testing:
# Test the server directly
npx @mmntm/weblate-mcp
Option 2: Development Setup
Prerequisites
- Node.js 18+
- pnpm package manager
- Weblate instance with API access
Installation
# Clone and install
git clone <this-repo>
cd weblate-mcp
pnpm install
# Configure environment
cp .env.example .env
# Edit .env with your Weblate API URL and token
# Build and start
pnpm build
pnpm start
Server runs on http://localhost:3001 by default.
Environment Configuration
WEBLATE_API_URL=https://your-weblate-instance.com
WEBLATE_API_TOKEN=your-api-token-here
PORT=3001
NODE_ENV=production
LOG_LEVEL=info
🔗 MCP Client Configuration
Claude Desktop (npx method - Recommended)
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"weblate": {
"command": "npx",
"args": ["-y", "@mmntm/weblate-mcp"],
"env": {
"WEBLATE_API_URL": "https://your-weblate-instance.com/api",
"WEBLATE_API_TOKEN": "your-weblate-api-token"
}
}
}
}
Claude Desktop (Development/Local)
For development or local builds:
{
"mcpServers": {
"weblate": {
"command": "node",
"args": ["/path/to/weblate-mcp/dist/main.js"],
"env": {
"WEBLATE_API_URL": "https://your-weblate-instance.com/api",
"WEBLATE_API_TOKEN": "your-api-token"
}
}
}
}
HTTP Clients (Cursor, VS Code, Web Apps)
{
"transport": "http",
"url": "http://localhost:3001/mcp"
}
🛠️ Available Tools
📊 Project Management
| Tool | Description |
|---|---|
list_projects |
List all projects in your Weblate instance |
get_project |
Get detailed information about a specific project |
create_project |
Create a new translation project |
🔧 Component Management
| Tool | Description |
|---|---|
list_components |
List all components in a project |
get_component |
Get detailed information about a component |
create_component |
Create a new translation component |
✏️ Translation Management
| Tool | Description |
|---|---|
list_translations |
List all translations for a component |
get_translation |
Get detailed information about a translation |
update_translation |
Update translation strings |
🌐 Language Management
| Tool | Description |
|---|---|
list_languages |
List all available languages |
get_language |
Get detailed information about a language |
💡 Usage Examples
Project Operations
// List all projects
await list_projects();
// Get specific project details
await get_project({ slug: "my-project" });
// Create a new project
await create_project({
name: "New Project",
slug: "new-project",
web: "https://example.com"
});
Translation Operations
// List translations for a component
await list_translations({
project_slug: "my-project",
component_slug: "frontend"
});
// Get specific translation
await get_translation({
project_slug: "my-project",
component_slug: "frontend",
language_code: "fr"
});
// Update translations
await update_translation({
project_slug: "my-project",
component_slug: "frontend",
language_code: "fr",
translations: {
"welcome": "Bienvenue",
"goodbye": "Au revoir"
}
});
📚 Documentation
| Document | Description |
|---|---|
| 📖 Documentation Hub | Complete documentation overview and quick start |
| 🚀 Installation & Setup | Installation, configuration, and Claude Desktop setup |
| 📋 API Reference | Complete API documentation with examples |
| 🛠️ Development Guide | Contributing, development setup, and testing |
| 🏗️ Architecture | Codebase structure, patterns, and design decisions |
| 📦 Release Process | Release management and publishing workflow |
| 🔄 Changesets Guide | Version management with changesets |
🏗️ Architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ MCP Client │───▶│ Weblate MCP │───▶│ Weblate API │
│ (IDE/Editor) │ │ Server │ │ (REST API) │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
▼
┌──────────────────┐
│ MCP Tools │
│ • Projects │
│ • Components │
│ • Translations │
│ • Languages │
└──────────────────┘
Technology Stack:
- NestJS: Modern Node.js framework with dependency injection
- TypeScript: Full type safety and IntelliSense support
- Weblate REST API: Comprehensive API wrapper with interfaces
- MCP Protocol: Standard Model Context Protocol implementation
- Axios: HTTP client for API communication
🧪 Development
Development Setup
# Start development server with hot reload
pnpm run dev
# Run tests
pnpm test
# Run end-to-end tests
pnpm run test:e2e
# Generate test coverage
pnpm run test:cov
# Build for production
pnpm build
Adding New Tools
- Create tool file in
src/tools/ - Implement MCP tool interface
- Add to service providers
- Write tests
- Update documentation
See Development Guide for detailed instructions.
🎯 Use Cases
Translation Management
- Project oversight: Monitor translation progress across projects
- Content updates: Update translations programmatically
- Quality assurance: Review and approve translations
- Team coordination: Manage translation workflows
Development Integration
- CI/CD pipelines: Automate translation updates in deployment
- Content management: Sync translations with content systems
- Localization testing: Validate translations in different contexts
- Documentation: Generate translation reports and statistics
AI-Assisted Workflows
- Natural language queries: Ask about translation status in plain English
- Contextual operations: AI understands your translation needs
- Batch operations: Perform bulk updates with AI assistance
- Smart suggestions: Get AI-powered translation recommendations
🔒 Security & Production
- API Token Security: Store tokens securely, use environment variables
- Rate Limiting: Built-in request throttling and retry logic
- Error Handling: Comprehensive error responses with debugging info
- Input Validation: All inputs validated with Zod schemas
- HTTPS Support: Secure communication with Weblate instances
🤝 Contributing
We welcome contributions! Please see our Contributing Guidelines:
- Fork the repository
- Create a feature branch from main
- Implement changes with tests
- Update documentation
- Submit a pull request
Code Style
- Use TypeScript for type safety
- Follow NestJS conventions
- Add comprehensive tests
- Update documentation
📄 License
MIT License - see LICENSE file for details.
🙏 Acknowledgments
- Weblate: For providing an excellent translation management platform
- Model Context Protocol: For the standardized protocol specification
- NestJS: For the robust application framework
- Contributors: Everyone who helps improve this project
Built with ❤️ for the translation community
Need help? Check our documentation or create an issue!
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.