Lokalise MCP. Manage i18n keys and translations from your chat.
Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Lokalise connects your AI agent directly to your translation and localization backend. Manage entire content pipelines—from creating new keys to uploading XLIFF files—all through conversation.
You can list projects, fetch translations for specific keys, or generate full download bundles without leaving your IDE.
What your AI agents can do
Add translation
Adds translated text strings to one or more specified keys within a project.
Create key
Creates a brand-new, unique translation key inside an existing Lokalise project.
Create project
Sets up and initializes an entirely new localization project in your account.
Retrieve the full metadata for a specific Lokalise project, including current status and linked languages.
Add new, unique translation keys to an existing Lokalise project so translators know what strings to fill in.
Modify the attributes of a key, such as renaming it or changing its associated tags, without altering the translations themselves.
Input actual translated strings for one or more keys, marking them with status flags like 'review' or 'fuzzy'.
Push entire content bundles—like JSON or XLIFF files—into a project to bulk-update many translation keys.
Create and download zip packages containing all translated strings for specific languages in formats like YAML or JSON.
Ask AI about this MCP
Supported MCP Clients
Waiting for input…
Lokalise MCP Server: 13 Tools for Localization Management
Orchestrate localization workflows by listing projects, creating keys, uploading file bundles, and retrieving translations using these core tools.
019d75c9add translation
Adds translated text strings to one or more specified keys within a project.
019d75c9create key
Creates a brand-new, unique translation key inside an existing Lokalise project.
019d75c9create project
Sets up and initializes an entirely new localization project in your account.
019d75c9download file
Generates a downloadable archive containing translations for selected languages and formats.
019d75c9get project
Fetches the detailed configuration and status of a single, specific Lokalise project.
019d75c9list keys
Retrieves a list of all translation keys in a project, allowing filtering by platform or tags.
019d75c9list languages
Shows every supported language available for localization within the current project scope.
019d75c9list orders
Retrieves a list of professional translation orders associated with your Lokalise account.
019d75c9list projects
Gives you an overview and name list of every project set up in your entire Lokalise account.
019d75c9list team members
Provides a roster of all users and their assigned roles within the organization's team structure.
019d75c9list translations
Lists the specific content strings (the actual translation) for a given key in a project.
019d75c9update key
Changes the name or attributes of an existing translation key within the project structure.
019d75c9upload file
Imports external localization files (like JSON or YAML) into a specified Lokalise project.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Lokalise, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Lokalise connects your AI agent straight to your translation backend. You manage your whole content pipeline—from setting up new keys to pushing out finished bundles—all through conversation. Your agent acts like a dedicated localization coordinator, letting you work right from your IDE or terminal.
To start managing translations, you first need the project details. Run list_projects and you'll pull an overview and name list of every single project in your account. If you need to set up a brand new locale, just call create_project to initialize it. To check the current status or get the full metadata for one specific job, use get_project.
This retrieves all the configuration details and linked languages for that particular localization effort.
When it comes to content strings—the keys themselves—you've got options. Use list_keys to pull a complete list of every translation key; you can filter that roster by platform or specific tags to narrow down what you need. If the project needs more room, call create_key and add a brand-new, unique translation key for translators to fill in.
You'll also want to know how many languages are supported right now; run list_languages to see every available language for that project scope. For existing keys, don't forget update_key; you can change the name or attributes of an old key without altering any translations already attached to it.
To actually populate content, use add_translation to input translated text strings for one or more keys; this tool lets you set status flags like 'review' or 'fuzzy' right when you enter the data. When dealing with big batches of content, you can push entire content bundles—like JSON or YAML files—into a project using upload_file.
If you need to see what strings have already been entered for any given key, run list_translations and it fetches that specific content. You'll find the full roster of keys listed by list_keys, which lets you see everything assigned to your project.
When the translation work is done, generating a final package is straightforward. Run download_file to create a zip archive containing all translated strings for selected languages and formats. Need to know who's working on this account? Use list_team_members; that pulls every user's name and their assigned role within the organization’s team structure.
You can also track payment status by using list_orders, which gives you a list of professional translation jobs associated with your account.
How Lokalise MCP Works
- 1 You subscribe to this server and enter your Lokalise API Token.
- 2 Your AI client uses the token to make calls, such as calling
list_keysto find assets orcreate_projectto start a new job. - 3 The agent receives structured data back (JSON/XML) that it processes before presenting you with actionable results in plain text.
The bottom line is: your AI client handles the API calls, keeping you out of the web console and straight into your code or chat window.
Who Is Lokalise MCP For?
Product Owners who get stuck waiting on translations. Developers building i18n features who hate context switching. Localization Managers who need to audit keys or pull export bundles fast. If you deal with content spread across many languages, this is for you.
You use the agent to instantly create_key strings and upload_file translations directly from your IDE, never leaving your coding environment.
You check translation progress across languages using tools like list_projects, monitoring key counts without logging into the web dashboard.
You automate bulk workflows, generating full download bundles via download_file and managing team orders with list_orders.
What Changes When You Connect
- Stop clicking through web dashboards. You can
list_projectsorget_projectdetails directly in the chat, giving you an immediate status check on a project's health. - Never manually create a key again. Use
create_keyto generate new translation strings and immediately push them into the workflow for translators to fill out. - Pulling data used to be painful. Now, use
download_fileto grab export bundles in YAML or JSON format instantly, ready for your build pipeline. -
upload_filelets you bulk-process localization assets. Just send it a file and the agent handles pushing those translations into the right project structure. - Check team status easily. Run
list_team_membersto see who's on the roster, or check professional work queues usinglist_orders, all from one prompt.
Real-World Use Cases
Need to Audit Content Keys Before a Release
The PM needs to know if every platform has been covered. They ask the agent to run list_keys and filter by 'platform: mobile'. The agent returns a clean list of only those keys, confirming no critical strings were missed before launch.
Rolling Out New Feature Strings Fast
A developer writes new UI text. Instead of going to Lokalise, they ask the agent to create_key for 'checkout.new_feature' and immediately use add_translation in multiple languages, getting confirmation it's ready.
Syncing Translations from a Build Artifact
The build pipeline generates a large JSON file of completed translations. Instead of manually uploading it, the developer asks the agent to run upload_file on the new artifact, getting it into the correct project.
Getting an Overview of All Content Assets
The team needs a bird's-eye view. They ask the agent to first list_projects to see all active sites, and then run get_project on the top two results to check their specific language counts.
The Tradeoffs
Trying to manage keys manually
Copying a key name from the Lokalise web console, pasting it into a spreadsheet, and then trying to remember which project it belongs to.
→
Use the agent. Run list_keys first to get an accurate list of available assets for that specific project. Then use get_project if you need more than just the key name.
Confusing file uploads with updates
Uploading a bundle of translations (upload_file) but forgetting to specify which language needs those strings updated.
→
Always confirm your target scope. When uploading, be ready to narrow down the required action by asking the agent to list_languages first, then confirming the correct upload format.
Creating keys without a clear purpose
Just generating random strings for testing without knowing if they are needed in the project's actual scope.
→
Before you run create_key, check what exists using list_keys. This prevents duplicate or unnecessary assets, keeping your content clean.
When It Fits, When It Doesn't
Use this server if managing translations is a primary part of your development lifecycle. You need to programmatically create, read, update, and delete localization keys and files across multiple projects. It's perfect for teams that use CI/CD pipelines or advanced IDE workflows.
Don't use it if you only ever check translation status once a month from the web dashboard. If your needs are limited to viewing data without any automation (like just checking team roles), manually using the Lokalise interface is fine. You might also be better off with a dedicated Git-based localization tool instead of an API gateway like this.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Lokalise. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 13 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Dealing with localization assets used to mean bouncing between five different browser tabs.
Remember the cycle: you check the project status on one tab, copy a key name into a spreadsheet, switch to another tab to find the correct language code, and then finally go back to the Lokalise web console just to hit 'save'. It’s slow, error-prone, and wastes minutes every hour.
With this MCP server, you run `get_project` in your chat client. The agent handles the status check, returns a clean summary, and lets you immediately use it to run `list_keys` for that project—all without opening another browser window. It's instant.
Lokalise MCP Server: Manage translation keys & files
The biggest time sink is file handling. You have a massive YAML or JSON bundle from your build, but manually pushing those strings into the right project and key is tedious. Then you need to run `list_translations` just to verify it worked.
Now, you simply ask the agent to `upload_file`. It processes the entire bulk upload, handles the metadata, and confirms success in one go. The integration point moves from a manual UI click to a single command.
Common Questions About Lokalise MCP
What kind of Lokalise API token do I need for this integration? +
You need a Personal Access Token from your Lokalise account. Go to your profile settings, find the API Tokens section, and generate a new token with read/write access to projects. Keep this token secure as it grants full API access to your account.
How do I add a new translation key to my Lokalise project via the AI agent? +
Use the create_key action with the project ID, key name (e.g., homepage.welcome.title), and optionally specify platforms, tags, and a description. The key will be created with the base language placeholder ready for translation.
Can I export all my translations in a specific format like JSON or YAML? +
Yes! Use the download_file action and specify the format parameter (e.g., json, yml, xliff, strings, xml). You can also filter by specific languages or filenames to generate targeted export bundles.
Is it possible to add translations programmatically for multiple languages at once? +
Yes. The add_translation action supports adding translations for one or more keys at once. You can also mark translations as fuzzy or reviewed to indicate their quality status in the workflow.
Before I start managing keys, how do I use `list_projects` to see all the Lokalise projects available? +
You simply run the list_projects tool through your AI agent. It returns a list of every project ID and name associated with your account. This lets you quickly select the right context before running any other operations, like creating keys or uploading files.
After I upload a file using `upload_file`, how can I use `list_translations` to audit specific key completion status in Lokalise? +
Running list_translations gives you the current localized values for any given key. You get structured data showing which languages have translations and when they were last updated, helping you spot gaps instantly.
If I try to run `update_key` with an existing Lokalise key, will the system overwrite it or throw an error? +
The server handles this by updating the provided field data for that specific key. It doesn't delete other metadata; you just send it the new value(s) you want to commit for that key.
When I use `download_file`, are there size limits or rate limits on how large a localization bundle can be? +
The tool generates download bundles in formats like JSON, YAML, and XLIFF. While local API rate limits apply, it manages standard industry-sized files without issue for bulk distribution.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Granola
Manage AI meeting notes via Granola — list and search meeting documents, retrieve transcripts and summaries, and track action items directly from any AI agent.
meetergo
Schedule meetings intelligently with routing rules that send leads to the right rep based on territory, availability, and deal size.
Gamma (AI Presentations)
Generate AI-powered presentations, documents, and webpages. List, update, and manage your Gamma workspace directly from any AI agent.
You might also like
Home River Group
Connect and manage Home River Group properties, units, and residents via Entrata API.
Meetup
Manage your Meetup groups — audit upcoming events, members, and details via AI.
HubSpot
Grow better with an integrated CRM that unifies marketing, sales, service, and operations in one powerful platform.