How to Use the Crowdin MCP in Mastra AI

Q: What's the difference between listglossaries and listtranslationmemories?

listglossaries gives you tools for terminology management for key terms. listtranslationmemories gives you databases of previously translated sentences for reuse.

Automate your Crowdin localization pipeline with Mastra AI. Build workflows that handle errors, retry, and just plain work.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crowdin MCP to Mastra AI

Create your Vinkius account to connect Crowdin to Mastra AI 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

Setup Crowdin with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Resilient Sync Workflows

Use Mastra AI to build automation that doesn't break. For instance, create a workflow to download all project cost reports. The agent starts with `list_projects`, then loops through each one to call `list_project_reports`. Here's the key: Mastra's engine handles the details. If a network call to the Crowdin MCP Server fails, it retries automatically with backoff. Your sync job will finish, even if the connection gets flaky.

Automate Localization QA Checks

Go beyond simple scripts. Build a stateful QA workflow. An agent can periodically run `list_project_tasks` to check for overdue proofreading jobs. When it finds one, Mastra's conditional logic kicks in. The workflow can then escalate the issue by triggering another action, like notifying a project manager. It's a proper autonomous process that reacts to the state of your Crowdin projects.

Enforce Terminology Standards

Consistency in translation is critical. You can build a Mastra AI workflow to enforce it. The agent can use `list_glossaries` and `list_translation_memories` to get a manifest of required resources. When a new project appears in `list_projects`, the workflow checks if the right TM and glossary are attached. If not, it can flag the project for human review. This stops inconsistent translations before they even start.

Setup guide

Set up Crowdin MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Crowdin tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "crowdin-mcp-client",
  servers: {
    "crowdin-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Crowdin Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Crowdin tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Crowdin transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crowdin. 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.

Why Choose Vinkius

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

Connect Crowdin now

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 Mastra AI

You create an agent in Mastra and give it access to this MCP Server's tools. Then you define your workflow logic, telling the agent to call tools like `list_project_tasks` and branch based on the results.

The agent can't generate reports itself, but it can find existing ones. It uses `list_project_reports` to see what's available. You can build a workflow that downloads new reports as soon as they appear.

Mastra has built-in retry logic with exponential backoff. If a call to a Crowdin tool fails, the agent will try again automatically, making your workflows much more reliable.

`list_glossaries` gives you tools for terminology management for key terms. `list_translation_memories` gives you databases of previously translated sentences for reuse.

The server accesses data needed for automation, including task details, report metadata, glossary names, and TM stats. Your Mastra agent connects via a single Vinkius endpoint, and the ephemeral instance is destroyed after your workflow runs.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript