4,500+ servers built on MCP Fusion
Vinkius
Crowdin logo
Vinkius
Claude Code logo

How to Use the Crowdin MCP in Claude Code

Pipe your Crowdin localization data directly into the terminal. This headless MCP server is built for your CI/CD pipelines and shell scripts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Crowdin MCP on Cursor AI Code Editor MCP Client Crowdin MCP on Claude Desktop App MCP Integration Crowdin MCP on OpenAI Agents SDK MCP Compatible Crowdin MCP on Visual Studio Code MCP Extension Client Crowdin MCP on GitHub Copilot AI Agent MCP Integration Crowdin MCP on Google Gemini AI MCP Integration Crowdin MCP on Lovable AI Development MCP Client Crowdin MCP on Mistral AI Agents MCP Compatible Crowdin MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Crowdin MCP to Claude Code

Create your Vinkius account to connect Crowdin to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Automate Localization QA in CI

Add a QA step to your build pipeline that checks your Crowdin project status. A simple script can use `list_project_files` to check for files with low translation coverage or `list_project_tasks` to find stalled proofreading tasks. If a file's translation progress is below 90%, you can fail the build. This MCP Server lets your CI system talk directly to Crowdin, catching localization issues before they hit production.

Script Project Health Checks

Write a shell script that runs nightly via cron. It can connect to this MCP server to perform health checks on your entire Crowdin account. Use `list_projects` and `get_project_details` to make sure every project has target languages defined. Chain that with `list_translation_memories` to confirm that each project is linked to a TM. You can pipe the output to a log file or send a notification if something's wrong. It’s set-and-forget monitoring for your localization workflow.

Headless Reporting for Claude Code

Don't log into the web UI just to download a report. Use `claude mcp` with the `list_project_reports` tool to pull data directly into your terminal. Pipe the output to `jq` to parse it or send it to another service. This is perfect for automated financial tracking or for sending weekly progress summaries to a Slack channel. You get the data you need, where you need it, with no manual steps.

Setup guide

Set up Crowdin MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see crowdin-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Crowdin transactions." It will automatically discover and invoke the available Crowdin tools.

Terminal
claude mcp add --transport http crowdin-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Crowdin MCP in Claude Code

In your workflow YAML, add a step that runs `claude mcp` with the `list_project_files` tool. You can parse the JSON output to check the `translationProgress` for each file and act accordingly.
Yes. Run `claude mcp` with the `list_supported_languages` tool. It will output a list of all language codes and names that Crowdin can handle.
Run `claude mcp add --transport http crowdin -- `. Then you can use `claude mcp rpc crowdin.list_projects` to start making calls.
This server lets you list TMs with `list_translation_memories` to get their IDs and segment counts. It doesn't provide a tool for downloading the actual TM file content itself.
The connection only exposes metadata: file structures, project configurations, task assignments, and glossary names. The content of your source files and translations is never accessed. Vinkius isolates each request in a zero-trust sandbox.

Start using the Crowdin MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Crowdin. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

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.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.