Let Claude, Cursor or any AI agent manage your translations with plain-language prompts. Connect with one URL, nothing to install.
SimpleLocalize hosts the MCP server for you. Add its URL to your AI client, sign in and choose what the agent can do. Nothing to install, nothing to host.
Add the server URL as a custom connector in Claude, or paste it into the MCP config of Cursor, VS Code or LM Studio. Claude Code needs a single command.
Sign in with your SimpleLocalize account and pick the projects and tools the agent can use. You can change them anytime.
Tell it to localize a component, fill missing translations or export files. The agent picks the right tools by itself.
Every change lands in the SimpleLocalize translation editor with full history, so your team and translators can review it.
For a step-by-step walkthrough, see the getting started guide.
Add https://api.simplelocalize.io/mcp to your AI client and sign in with your SimpleLocalize account. Connect it once and every chat can read, create and publish translations in the projects you chose.
https://api.simplelocalize.io/mcp
In Claude, go to Settings > Connectors, click Add custom connector, paste the URL and click Connect.
The server exposes SimpleLocalize as MCP tools with typed parameters,
so the agent knows exactly what it can do and what each call changes.
Create, update, rename and delete keys, one or hundreds at a time. Read key details, metadata and paginated lists, and attach screenshots for context.
Read translations for any language and namespace, and update one or hundreds of them at once straight from the code the agent just wrote.
Translate a string on the fly without saving it, or start auto-translation jobs with DeepL, Google Translate or OpenAI and check their progress.
Export translations to any of the supported formats: JSON, YAML, XLIFF, PO, iOS strings, Android XML and more.
List and create hosting environments, inspect their details and publish translations to translation hosting from a single prompt.
Manage glossary entries, tags, project languages and customer-specific translations. Read project details and the activity log to see what changed.
You do not need to learn tool names. Describe the outcome and the agent chains the right calls.
“Localize this React component and push the new translation keys to SimpleLocalize”
“Find translation keys without a German translation and auto-translate them with DeepL”
“What changed in the project since yesterday?”
“Publish the latest translations to production”
“Export the pl‑PL translations as a single-language JSON file into src/locales”
“Add a glossary entry so that 'SimpleLocalize' is never translated”
“Attach this screenshot to the checkout keys so translators see the context”
The server uses the standard Streamable HTTP transport with OAuth sign-in, so it works in any client that supports the Model Context Protocol.
Model Context Protocol (MCP) is an open standard that lets AI agents call external tools. The SimpleLocalize MCP server exposes translation keys, translations, auto-translation, import, export and hosting as tools, so an agent like Claude or Cursor can manage localization in your project from a natural language prompt.
Yes. The server is free to use. It requires a SimpleLocalize project, and the free plan is enough to try it. Auto-translation usage counts against the characters included in your plan, exactly as it does in the web editor.
Clients like Claude, Claude Code, Cursor and VS Code open a SimpleLocalize sign-in page, where you choose the projects and tools the app can use. You can change them or disconnect the app anytime in Security > Connected apps. Clients without sign-in support can send a Personal Access Token or a Project API Key in a header instead.
The server itself only talks to the SimpleLocalize API. Whatever the agent reads through a tool becomes part of the conversation with your chosen AI client, the same as any file the agent opens. Auto-translation runs on the provider you configured in SimpleLocalize, for example DeepL, Google Translate or OpenAI.
In the cloud. SimpleLocalize hosts the server at https://api.simplelocalize.io/mcp, so there is nothing to install or keep up to date. The earlier npm package that ran locally with npx is deprecated.
The CLI is for scripted, repeatable synchronization in your build or CI. The VS Code and IntelliJ extensions are for editing translations by hand inside the IDE. The MCP server is for delegating localization tasks to an AI agent. Many teams use all three: the agent adds keys, the extension reviews them, the CLI ships them.
Only if you leave delete tools enabled when you connect the app; you can unselect them on the sign-in page or later in Security > Connected apps. Delete tools are also annotated as destructive, so clients such as Claude ask for confirmation before running them. Every change is recorded in the project activity log and can be reviewed in the translation editor.
See the latest news from our blog, including product updates, tutorials, and more.

The official SimpleLocalize MCP Server allows you to integrate AI agents like Cursor AI, Claude, or GitHub Copilot with SimpleLocalize for managing translations in your projects.

Learn how to integrate OpenRouter with SimpleLocalize for enhanced auto-translation capabilities. Ai-powered localization made easy!

Discover how SimpleLocalize helps enterprise SaaS teams scale localization across dozens of locales without the complexity of legacy TMS platforms.

Use AI-powered workflows to speed up software localization, integrate with CI/CD pipelines, and ensure translations are accurate, consistent, and release-ready.

The official SimpleLocalize MCP Server allows you to integrate AI agents like Cursor AI, Claude, or GitHub Copilot with SimpleLocalize for managing translations in your projects.
The SimpleLocalize MCP server connects AI coding agents with a translation management system. Instead of copying strings between your code editor and a localization tool, you ask the agent to extract texts, create translation keys, fill missing translations and export files in the format your framework expects. The server implements the Model Context Protocol, the same standard used by Claude, Cursor, GitHub Copilot, Windsurf and a growing list of clients, and calls the SimpleLocalize REST API under the hood.
A typical workflow starts in the code: the agent localizes a component with your i18n library, creates the keys in SimpleLocalize and adds source translations. Next it runs auto-translation for the missing languages, optionally guided by your glossary. Translators and reviewers work in the translation editor, and the agent or the SimpleLocalize CLI pulls the finished translations back into the repository or publishes them to translation hosting.
The server is hosted by SimpleLocalize and covers translation keys, translations, screenshots, auto-translation jobs, tags, languages, customers, glossary, hosting environments, export and project activity. New tools are available in every connected client without updates. The earlier @simplelocalize/simplelocalize-mcp npm package is deprecated; to migrate, replace its npx entry with the server URL, as described in the setup guide.