Compatible with every major AI agent and IDE
What is the Weblate MCP Server?
Connect your Weblate instance to any AI agent to streamline your continuous localization and translation management through natural conversation.
What you can do
- Project & Component Management — List all projects, fetch component details, and explore translation files directly from the Weblate API.
- Language Insights — Retrieve detailed statistics for specific languages to track translation progress and identify missing strings.
- User & Group Administration — Manage user profiles, list contributions, and handle group roles or administrative permissions.
- Repository Operations — Perform critical repository actions like pulling updates or pushing translations to keep your version control in sync.
- Notification Control — List and manage user notification subscriptions to stay updated on translation changes.
How it works
- Subscribe to this server
- Enter your Weblate Instance URL and Personal API Token
- Start managing your localization projects from Claude, Cursor, or any MCP-compatible client
No more switching between your IDE and the Weblate dashboard to check translation status or user permissions. Your AI acts as a localization manager.
Who is this for?
- Localization Managers — quickly check project health, language coverage, and user contributions without manual reporting.
- Developers — trigger repository syncs and inspect component structures directly from the code editor.
- DevOps Engineers — automate user provisioning and group role assignments within the localization infrastructure.
Built-in capabilities (32)
Add team administrators to a group
Associate roles with a group
Create a new group
Create a new language definition
Create a new project
Create a new component in a project
Create a new role with specific permissions
Create a new Weblate user
Delete a user (marks inactive)
Get group details (roles, projects, components)
Get language details (plural formulas, aliases)
Global statistics for a language
Get project details
Get the URL to download all translations as a ZIP archive
Overall VCS status for the project
Get role details and permission codenames
Get Weblate API root entry point
Get detailed user information
List translations with user contributions
Get user translation statistics
List Weblate groups
List all languages
List components within a project
Manage project labels
Paginated statistics for all languages in a project
List all projects
List roles associated with the user
List user notification subscriptions
Requires management permissions or returns self. List Weblate users
Manage user notification subscriptions
Perform VCS operations (push, pull, commit, reset, cleanup)
Update user details
Why Cursor?
Cursor's Agent mode turns Weblate into an in-editor superpower. Ask Cursor to generate code using live data from Weblate and it fetches, processes, and writes. all in a single agentic loop. 32 tools appear alongside file editing and terminal access, creating a unified development environment grounded in real-time information.
- —
Agent mode turns Cursor into an autonomous coding assistant that can read files, run commands, and call MCP tools without switching context
- —
Cursor's Composer feature can generate entire files using real-time data fetched through MCP. no copy-pasting from external dashboards
- —
MCP tools appear alongside built-in tools like file reading and terminal access, creating a unified agentic environment
- —
VS Code extension compatibility means your existing workflow, keybindings, and extensions all work alongside MCP tools
Weblate in Cursor
Weblate and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Weblate to Cursor through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Weblate in Cursor
The Weblate MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 32 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Cursor only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Weblate for Cursor
Every tool call from Cursor to the Weblate MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
What is Agent mode and why does it matter for MCP?
Agent mode is Cursor's autonomous execution mode where the AI can perform multi-step tasks: reading files, editing code, running terminal commands, and calling MCP tools. Without Agent mode, Cursor operates in a simpler ask-and-answer mode that doesn't support tool calling. Always ensure you're in Agent mode when working with MCP servers.
Where does Cursor store MCP configuration?
Cursor looks for MCP server configurations in a mcp.json file. You can configure servers at the project level (.cursor/mcp.json in your project root) or globally (~/.cursor/mcp.json). Project-level configs take precedence.
Can Cursor use MCP tools in inline edits?
No. MCP tools are only available in Agent mode through the chat panel. Inline completions and Tab suggestions do not trigger MCP tool calls. This is by design. tool calls require user visibility and approval.
How do I verify MCP tools are loaded?
Open Settings → Features → MCP and look for your server name. A green indicator means the server is connected. You can also check Agent mode's available tools by clicking the tools dropdown in the chat panel.
Tools not appearing in Cursor
Ensure you are in Agent mode (not Ask mode). MCP tools only work in Agent mode.
Server shows as disconnected
Check Settings → Features → MCP and verify the server status. Try clicking the refresh button.
Explore More MCP Servers
View all →
Diffbot
10 toolsAutomate web data extraction via Diffbot — turn any website into structured JSON data for articles, products, discussions, and more directly from any AI agent.

Clarifai (Vision AI)
6 toolsManage AI inference via Clarifai — list apps, models, and workflows, and perform computer vision predictions directly from any AI agent.

Hetzner
38 toolsManage Hetzner Cloud infrastructure—list servers, manage firewalls, and control power states directly from any AI agent.

Addepar
5 toolsInvestment management and reporting — manage portfolios, accounts, and financial performance via AI.
