Supercharge your AI with Weblate. Manage all localization governance from your agent.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Weblate MCP automates continuous localization workflows by letting your agent manage projects, users, languages, and components directly. You can check project health, track language completion rates, assign group roles, or even pull repository updates without ever logging into the WebLate dashboard.
It puts full content governance power right inside your code editor.
What your AI can do
Add group admins
Assigns team administrators to a specific group.
Add group roles
Links defined roles to an existing group.
Create group
Sets up a new user group within Weblate.
Fetch detailed stats on languages or projects to see what needs translating and where.
Create, delete, and assign administrative roles for users and groups across the platform.
List specific translations or pull usage statistics tied to a single user account.
Create new projects, languages, or component sections within existing translation files.
Perform version control operations like pulling updates or pushing translations to the repository.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 Compatible Gemini Waiting for input…
Weblate MCP with 32 Tools
These tools let you perform every administrative action in Weblate: from creating new projects to updating user roles and performing version control operations.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Weblate on VinkiusAdd Group Admins
Assigns team administrators to a specific group.
Add Group Roles
Links defined roles to an existing group.
Create Group
Sets up a new user group within Weblate.
Create Language
Defines and registers a brand-new language for the system to track.
Create Project Component
Adds a specific piece of text or component structure to an existing project.
Create Project
Initiates a completely new localization project.
Create Role
Defines a new set of permissions and roles available in the system.
Create User
Creates a brand-new user account for Weblate.
Delete User
Deactivates a user account, marking it inactive without deleting data.
Get Group
Retrieves full details about a specific group, including its roles and associated...
Get Language
Fetches structural data for a language, like plural formulas or aliases.
Get Project
Gets detailed information about a specific localization project, including its scope.
Get Role
Retrieves detailed information and permission codes for a defined role.
Get User
Retrieves comprehensive profile details for a specified user.
List Groups
Retrieves a list of all existing groups in the Weblate instance.
Get Language Statistics
Provides global metrics and progress reports for an entire language across all...
List Languages
Lists every language that has been defined in the system.
List User Notifications
Shows which users have subscribed to receive specific notification alerts.
Manage User Notifications
Allows you to manage and update which notification subscriptions are active for users.
List Project Components
Shows all individual components (text snippets) within a given project's structure.
Get Project File Url
Generates a URL that lets you download all translations for a project as a ZIP file.
List Project Labels
Manages and lists metadata labels applied to specific projects.
List Project Languages
Presents paginated statistics, showing language coverage for all languages in a...
Perform Repository Operation
Executes core version control tasks like pushing, pulling, or resetting the project history.
Get Project Repository
Checks the overall version control status of the entire localization project.
List Projects
Lists every single localization project currently set up in the system.
List Roles
Retrieves a list of all defined roles associated with user management.
Get Root
Accesses the main entry point of the Weblate API.
Update User
Changes details for an existing user account, such as their email or name.
Get User Contributions
Lists all translations that were added or edited by a specific user.
Get User Statistics
Provides personal translation metrics and usage data for an individual user.
List Users
Returns a list of all user accounts, requiring management permissions to view...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token from
cloud.vinkius.com. For OAuth-protected servers, expand Advanced
settings to add credentials.
Start a conversation
Open a new chat. The Weblate integration is available immediately — no restart needed.
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 Weblate, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ 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
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Weblate. 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 connection provides 32 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking Translation Status Is a Dashboard Nightmare.
Right now, checking if your localized content is ready means opening the WebLate site. You check Project A's dashboard for language completion. Then you switch tabs to Group B's permissions. If you want project metadata, you click into a different section entirely. It's constant clicking, copy-pasting stats, and cross-referencing spreadsheets just to get one answer: Is the German content ready?
With this MCP, that whole process vanishes. You ask your agent for the status—for example, 'What is the translation progress of all languages in the Mobile App project?' It executes a command like `list_project_languages` and hands you a single, definitive answer without opening any external tabs.
Create Project and Component Management
Manually setting up localization involves creating the project container first. Then, for every new feature or module, you have to go into WebLate and manually add the corresponding component section. If you forget a step, the whole system breaks when you try to pull code.
Now, your agent handles it all. You tell it to 'Start a new e-commerce project' (using `create_project`), and then immediately tell it to 'Add the product listing component for that project' (`create_project_component`). It builds the structure correctly, every time.
What your AI can actually do with this
Stop jumping between dashboards to check translation status or user permissions. This MCP lets you manage complex localization projects through natural conversation. You can ask for a list of all active projects, pull detailed statistics on language completion rates, or confirm which group roles need updating—all without leaving your IDE.
Need to onboard a new team member? Your agent handles the whole process: it creates the user, assigns them to groups, and sets their initial permissions. Want to keep your version control clean? The connector lets you pull project repository updates directly from your terminal. Because Vinkius manages every call through a zero-trust proxy, your API keys never sit on disk; they only pass in transit.
This makes it safe to build complicated workflows that combine Weblate with other services, letting your agent act as the central localization manager for your entire stack.
019e3909-dc97-7022-a91b-7879639bb5ae 
Here's how it actually works
The bottom line is, it treats your entire localization backend as just another API endpoint your agent can talk to.
Subscribe to this MCP and enter your Weblate Instance URL along with your personal API token.
Ask your agent for a specific action, like 'List all projects that need German translation stats.'
The agent executes the command, reads the data, and gives you a clear answer without needing to open any external dashboards.
Who is this actually for?
Localization Managers who spend all day clicking between dashboards. Developers who get frustrated pulling repository updates manually. DevOps engineers needing to automate user provisioning and group role assignments across the whole system.
Checking project health, running language statistics (e.g., list_project_languages), and managing who can approve translations.
Triggering repository syncs (perform_repository_operation) or inspecting component structures directly from the code editor to ensure translation files are correct.
Automating user setup by creating new accounts (create_user), defining groups, and assigning administrative permissions (add_group_admins).
What Changes When You Connect
Check language completeness instantly. Instead of manually cross-referencing spreadsheets, you can get current statistics for a language using get_language_statistics and know exactly which strings are missing.
Control user access at scale. You don't need to touch the UI to manage who does what. Use tools like create_user, list_groups, or add_group_admins to provision entire teams with a single prompt.
Keep your code synced without manual effort. When you know translations are updated, use perform_repository_operation to pull the changes directly into your local environment. It's immediate.
Build complex automations. Combine this MCP with others through Vinkius and chain it up—for example, trigger a message send (messaging MCP) right after you confirm project status using get_project. The workflow is seamless.
Know exactly who did what. When troubleshooting, use get_user_contributions or get_user_statistics to trace specific changes back to the exact user responsible.
Maintain clean data structures. Need a new language for an upcoming market? Use create_language and then define it as part of a project using create_project_component.
See it in action
The QA team needs to check if all localized files are ready.
Instead of opening the dashboard and clicking through country-specific reports, you ask your agent to run list_project_languages for the 'French' project. The agent returns a clean summary showing which languages have passed 90% completion and which ones are lagging.
A new team needs full access, but only limited to certain components.
You use your agent to execute the workflow: first run get_group to confirm the target group exists. Then, you call add_group_roles, followed by create_user for the new hire, ensuring they can't access sensitive areas.
The Dev team needs to merge translated content into the main branch.
You trigger a clean pull of translations using perform_repository_operation. The agent confirms the status and then uses get_project_repository to verify that all changes have been committed successfully.
The PM needs to audit who has edited which strings.
You ask your agent to list contributions for 'johndoe' using get_user_contributions. It pulls a detailed list, showing every specific component and the exact time of the edit.
The honest tradeoffs
Just listing users.
A manager runs list_users and sees 50 people. They then have to manually figure out which ones are reviewers, who is an admin, and what groups they belong to.
Don't just list them. Use the agent to find a specific user's profile with get_user, or if you need group details, call get_group to see exactly who has what access.
Trying to manage permissions manually.
The team uses separate tools for creating projects and updating roles. The process is slow, requires jumping between interfaces, and often leads to misassigned permissions.
Use the agent to handle governance steps in order: first create_project, then define a role with create_role, and finally assign it using add_group_roles. It keeps the whole sequence clean.
Assuming all projects have components.
A developer tries to pull component details for a project that only exists as a shell. The system fails, leaving them stuck.
Always check first using get_project before calling list_project_components. This confirms the scope and structure are ready for work.
When It Fits, When It Doesn't
Use this MCP if your problem involves governance or status tracking. Specifically, you need to know who can do what (use get_group, list_roles), or you need a high-level summary of project health across multiple languages (get_language_statistics). Don't use it just because you want to read the source code; if your only goal is pure translation drafting, another tool might be better. If you are building an automation that needs to manage users and check repository status, this MCP is essential because of its breadth of tools (from list_users to perform_repository_operation).
Questions you might have
How do I check language statistics using the get_language_statistics tool? +
You just ask your agent for it. You provide the target language code (like 'de' or 'es'). The MCP runs get_language_statistics and returns a progress report, showing completion percentage and how many strings need attention.
Can I use list_users to see who can access my project? +
No. list_users only gives you a roster of accounts. To understand permissions or groups, you need to call get_group first, which links users to their specific roles and projects.
What is the difference between create_user and update_user? +
create_user makes an account from scratch for a person. update_user, however, modifies details (like changing an email address) on an existing user profile.
I need to sync my code repository after translations change; which tool do I use? +
You must use perform_repository_operation. This executes the necessary version control commands, letting you pull or push changes and keeping your project history accurate.
How does using get_role help me understand what specific permissions I can assign when running create_role? +
The tool provides a detailed breakdown of all permission codenames and capabilities for any role. Reviewing these details lets you build roles with only the necessary minimum access, which is key to maintaining proper security separation.
If I need to see every individual text component within a project before translating it, what should I use list_project_components for? +
It lists all the separate components inside your target project. This function is crucial because it allows you to scope exactly which pieces of content require translation effort, preventing missed strings.
Where do I find the link to download a ZIP archive of all translations for an entire project using get_project_file_url? +
The tool returns the direct URL needed for bulk downloads. You use this link to retrieve every translation across all languages as a single ZIP archive, which is perfect for offline auditing or review.
I want to assign admin rights to specific team members without giving them full system access; how do I manage that with add_group_admins? +
This function adds administrators directly to a defined group. Since permissions are tied to the group, you limit their elevated rights only to the scope of that group, keeping global platform control restricted.
Can I check the translation progress for a specific language code? +
Yes! Use the get_language_statistics tool with the language code (e.g., 'fr'). The agent will return detailed metrics including translated, fuzzy, and failing strings.
Is it possible to trigger a Git pull or push from the AI? +
Absolutely. Use the perform_repository_operation tool. You can specify the project and component along with the operation (like 'pull' or 'push') to sync with your remote repository.
Can I manage user access and view their contributions? +
Yes. You can use list_users to see accounts, get_user_contributions to audit translation activity, and add_group_roles to manage permissions programmatically.
We've already built the connector for Weblate. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 32 tools are live and waiting.
You're up and running in seconds.
Gemini Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.