How to Use the DeepL MCP in Mastra AI

Q: How do I add DeepL tools to a Mastra AI agent?

Install @mastra/mcp and instantiate the client with the Vinkius URL. Use listTools() to pull the translation tools and spread them directly into your Mastra AI agent's tool array.

Q: How do I manage DeepL glossaries inside Mastra AI?

Your MCP agent can use createglossary and listglossaries to build and retrieve dictionaries on the fly. You can chain these actions into a multi-step workflow that prepares dictionaries before running translations.

Q: How does this server protect my glossary entries?

Your dictionary data sent to createglossary is isolated within Vinkius's secure, zero-trust sandbox. No glossary terms or translation payloads are stored on the Vinkius proxy infrastructure, maintaining complete data isolation.

Build resilient translation workflows with Mastra AI and DeepL to automatically handle retries and conditional tone shifts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepL MCP to Mastra AI

Create your Vinkius account to connect DeepL 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 DeepL with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Conditional translation branching with Mastra AI

The `translate_text` tool integrates directly into your Mastra AI workflow steps to handle raw text conversion. If a translation fails due to rate limits, this MCP Server keeps your production pipelines running by automatically retrying the call with exponential backoff. This keeps your production pipelines running without manual intervention. You can write step logic that checks `get_usage` before running large batches. If your API quota is near its limit, your workflow can branch to notify administrators or pause execution, saving you from unexpected runtime errors.

Automated glossary management in agent workflows

The `create_glossary` tool lets your agents build custom dictionaries programmatically during workflow execution. Your Mastra AI MCP agent can parse incoming brand assets, extract terms, and register them instantly. This guarantees that subsequent translations match your exact specifications. To keep things clean, use `delete_glossary` inside a cleanup step once a localized campaign goes live. This keeps your dictionary list tidy and prevents outdated rules from skewing your future translation jobs.

Human-in-the-loop tone validation

The `translate_formal` and `translate_informal` tools allow your workflows to adapt output style based on customer metadata. You configure Mastra AI to route professional communications to the formal engine while keeping social media replies casual. By enabling `requireToolApproval` on these tools, you can pause the workflow for manual review before sending the translated output to production. This gives your team a chance to inspect the tone before any external system receives the data.

Setup guide

Set up DeepL 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 DeepL 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: "deepl-alternative-mcp-client",
  servers: {
    "deepl-alternative-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent DeepL 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 DeepL. 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 DeepL 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 DeepL MCP in Mastra AI

Install `@mastra/mcp` and instantiate the client with the Vinkius URL. Use `listTools()` to pull the translation tools and spread them directly into your Mastra AI agent's tool array.

Yes. Mastra AI uses a workflow engine that supports automatic retries with exponential backoff. If `translate_text` hits an API limit, the system pauses and retries without crashing your pipeline.

Your MCP agent can use `create_glossary` and `list_glossaries` to build and retrieve dictionaries on the fly. You can chain these actions into a multi-step workflow that prepares dictionaries before running translations.

The MCP client automatically detects whether the Vinkius endpoint is running over Streamable HTTP or SSE. You do not need to manually configure the transport layer in your code.

Your dictionary data sent to `create_glossary` is isolated within Vinkius's secure, zero-trust sandbox. No glossary terms or translation payloads are stored on the Vinkius proxy infrastructure, maintaining complete data isolation.

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