Your AI Assistant Can Now Manage Your Locize Translations
The Locize ecosystem already handles the mechanical parts of localization well. Keys get reported automatically via saveMissing, the CLI instruments your codebase, and your CI pipeline publishes on deploy. That part is largely solved — if you're using those tools.
For everyone building with AI coding agents, the Locize MCP server can do all of that for you too. Describe what you need in plain language and let the assistant handle it.
And for both groups, there's a layer of conversational, exploratory work that no automation has addressed until now. Checking translation coverage before a release. Understanding which namespaces are lagging in which languages. Creating a branch for a feature, working through it, then merging it back. Renaming a namespace after a refactor. These tasks are quick to do but they pull you out of your current context — editor, terminal, or AI chat — and into a browser tab.
The Locize MCP server brings that management layer into your AI assistant. Ask Claude to check coverage, publish a version, or create a branch. It handles it directly, without the tab switch.
What is MCP?
Model Context Protocol is an open standard that lets AI assistants connect to external tools and services. Instead of copying and pasting context into a chat window, the AI can read from and write to your actual systems — with your explicit authorization.
Claude Desktop, Cursor, VS Code, and a growing list of other tools support it natively.
Connecting in 60 Seconds
Claude Desktop / claude.ai
- Go to Settings → Connectors → Add custom connector
- Enter the URL:
https://mcp.locize.app - Click Connect — your browser opens a Locize login screen
- Sign in and grant the requested permissions
That's it. A Personal Access Token is created automatically in your profile and can be revoked at any time.
Claude Code (CLI)
claude mcp add --transport http locize https://mcp.locize.appThen run /mcp in your session to complete the authorization.
Cursor, VS Code, and other clients
Add https://mcp.locize.app as a remote MCP server in your client's settings and follow the OAuth flow.
What You Can Do
Once connected, you talk to your translation projects in plain language. Here are some things that actually work today:
Finding gaps before a release:
"Find all missing German translations in the checkout namespace of my main project."
The assistant fetches the reference language and target language, compares them with full plural-form awareness, and returns the exact keys that need attention — with their English values so you know what needs translating.
Reporting new keys from a codebase conversation:
"I just added these three strings to the Settings page. Report them to Locize as missing keys in the latest version."
The assistant calls report_missing_keys — which only adds new keys and never overwrites existing translations, so it's safe to run at any point.
Publishing as part of a deploy conversation:
"We're deploying v2.3 in 10 minutes. Publish the production version of my project."
The assistant publishes the version and waits for the job to complete, reporting back when the CDN is updated.
Branch workflows:
"Create a branch from the latest version for the checkout redesign feature, then merge it back when I'm done."
Project management:
"Add Japanese to all versions of my project." "Rename the 'payment' namespace to 'checkout' across all languages." "What's the current translation coverage for each language in the production version?"
Available Tools
The MCP server exposes 22 tools organized around the full translation workflow:
| Group | Tools |
|---|---|
| Discovery | list_projects, get_project_stats, list_branches, list_tenants |
| Content | get_translations, get_published_translations, find_missing_translations, report_missing_keys, update_translations |
| Release | publish_version, copy_version, copy_language, get_job_status |
| Branches | create_branch, merge_branch |
| Structure | add_language, remove_language, change_languages, add_version, delete_version, rename_namespace, delete_namespace |
Authentication and Access Control
The MCP server supports two authentication methods.
OAuth 2.0 is used automatically by Claude Desktop, Cursor, and other MCP-native clients. When you connect, you log in with your existing Locize account and choose which permissions to grant. A Personal Access Token is created in your profile representing that authorization — you can see exactly which client created it and revoke it with one click.
Personal Access Tokens can also be used directly for CI/CD pipelines, scripts, or any client that doesn't support OAuth. Create one in your profile under Personal Access Tokens and pass it as a Bearer token. PATs carry explicit scopes (read, write, manage, admin) so you can grant the minimum permissions needed for each use case.
A Note on Multi-tenant and Branch Projects
The MCP server handles the full complexity of your Locize setup. For tenant and branch projects, translations are automatically merged with the parent project when reading — the same way the editor works. find_missing_translations understands tenant overrides and correctly identifies what's genuinely missing versus what falls back to the parent.
What's Next
This is the first release. The 22 tools cover the workflows that matter most day-to-day. Based on usage we'll add more.
The full documentation is here, including alternative setup options and all 22 tool descriptions.
Try it — the setup really does take about 60 seconds.