Phrase MCP Server
A Model Context Protocol server that integrates with Phrase Strings to manage translation projects, keys, and translations. Enables AI assistants to perform CRUD operations on projects, locales, and translations programmatically.
README
Phrase MCP Server
A Model Context Protocol (MCP) server that provides seamless integration with Phrase Strings, the translation management platform. This server enables AI assistants to interact with your Phrase projects, manage translation keys, and handle translations programmatically.
Features
- Project Management: List, view, and create Phrase projects
- Translation Keys: Create, read, update, and delete translation keys
- Translations: Manage translations across multiple locales
- Locale Management: Configure and manage project locales
- Search & Filter: Query keys and translations with flexible filters
Installation
Prerequisites
- Python 3.10 or higher
- uv package manager
- A Phrase account with API access
Setup
- Clone the repository:
git clone https://github.com/yourusername/phrase-mcp-server.git
cd phrase-mcp-server
- Install dependencies using uv:
uv sync
- Create a
.envfile with your Phrase API token:
cp .env.example .env
- Edit
.envand add your Phrase API token:
PHRASE_API_TOKEN=your_phrase_api_token_here
You can generate an API token in your Phrase account at: https://app.phrase.com/settings/oauth_access_tokens
Usage
Running the Server
The server uses stdio for communication with MCP clients:
uv run python -m phrase_mcp_server
Configuring with Claude Desktop
Add this to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"phrase": {
"command": "uv",
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/phrase-mcp-server",
"run",
"python",
"-m",
"phrase_mcp_server"
],
"env": {
"PHRASE_API_TOKEN": "your_phrase_api_token_here"
}
}
}
}
Replace /ABSOLUTE/PATH/TO/phrase-mcp-server with the actual path to your project directory.
Available Tools
The server provides the following tools:
Projects
list_projects- List all projects in your accountget_project- Get details about a specific projectcreate_project- Create a new project
Translation Keys
list_keys- List translation keys in a projectget_key- Get details about a specific keycreate_key- Create a new translation keyupdate_key- Update an existing keydelete_key- Delete a translation key
Translations
list_translations- List translations (optionally filter by locale)get_translation- Get a specific translationcreate_translation- Create a new translationupdate_translation- Update an existing translation
Locales
list_locales- List all locales in a projectget_locale- Get details about a specific localecreate_locale- Create a new locale
Example Usage
Once configured, you can ask Claude to interact with your Phrase projects:
"Show me all my Phrase projects"
"Create a new translation key 'welcome_message' in project XYZ with description 'Welcome screen greeting'"
"List all English translations in the mobile app project"
"Update the German translation for key 'app.title' to 'Meine Anwendung'"
Development
Project Structure
phrase-mcp-server/
├── src/
│ └── phrase_mcp_server/
│ ├── __init__.py
│ ├── __main__.py
│ ├── server.py # Main MCP server implementation
│ └── client.py # Phrase API client
├── pyproject.toml
├── .env.example
└── README.md
Running Tests
uv run pytest
Code Quality
The project uses modern Python practices:
- Type hints throughout
- Async/await for I/O operations
- Comprehensive error handling
API Reference
This server uses the Phrase Strings API v2. For detailed information about API endpoints and parameters, refer to the official Phrase API documentation.
Legal & Open Source
This is an unofficial community project and is not affiliated with or endorsed by Phrase. The server:
- Uses Phrase's official public API
- Requires users to provide their own API credentials
- Does not redistribute any Phrase proprietary content
- Provides only an interface to access Phrase services
License
MIT License - see LICENSE file for details.
Disclaimer
This software is provided "as is", without warranty of any kind. Users are responsible for complying with Phrase's Terms of Service and API usage policies.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
Support
For issues related to:
- This MCP server: Open an issue on GitHub
- Phrase API: Contact Phrase Support
- MCP Protocol: See Model Context Protocol docs
Changelog
0.1.0 (2026-01-14)
- Initial release
- Support for projects, keys, translations, and locales
- Full CRUD operations for all resource types
- Search and filtering capabilities
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.