How to Use the DeepL MCP in Vercel AI SDK

Q: How do I stream DeepL translations using Vercel AI SDK?

Install @ai-sdk/mcp and call createMCPClient pointing to the Vinkius endpoint. Pass the tools returned by mcpClient.tools() into streamText to let your agent call translatetext and output results directly to your React components.

Q: Can I use DeepL glossaries dynamically within Vercel AI SDK?

Yes. Your agent can call translatewithglossary by referencing glossary IDs found via listglossaries. This lets your Vercel AI SDK application enforce brand-specific terms during live translation streams.

Q: How do I switch between formal and informal DeepL tones in Vercel AI SDK?

Your agent chooses between translateformal and translateinformal based on the system prompt you configure. Pass these tools to your model configuration so it selects the correct tone dynamically during runtime.

Q: How do I clean up the connection after a translation run?

Always call mcpClient.close() once your translation tasks are complete. This prevents hanging HTTP connections in your serverless or Edge environment, keeping your resource usage within Vercel's limits.

Q: Is my translation text secure when using this server?

Yes. All raw text strings sent to translatetext pass through Vinkius's ephemeral V8 Isolate Sandbox. Your translation payloads are processed in a zero-trust environment and are never cached or logged on Vinkius servers.

Feed real-time DeepL translations directly into your React UI using Vercel AI SDK without waiting for slow background API runs.

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 Vercel AI SDK

Create your Vinkius account to connect DeepL to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time translation streaming with Vercel AI SDK

The `translate_text` tool handles instant translation of strings across 30+ language pairs. When you trigger this through your Vercel AI SDK setup, the translated tokens render on the user's screen as they arrive. This beats the standard pattern of showing a blank loading spinner while waiting for a heavy API payload to resolve. You can dynamically control the tone of the output by routing inputs to `translate_formal` or `translate_informal` based on user profile settings. Because this MCP Server hooks directly into your streamText call, your frontend gets raw, structured translations with zero intermediate backend boilerplate to write.

Live glossary injection in Edge Functions

The `translate_with_glossary` tool applies your specific terminology rules to text blocks before they hit your Next.js frontend. You initialize this tool inside an Edge Function to keep latency low. This MCP client matches raw user input against your custom dictionaries on the fly. Your application manages these rules dynamically using `create_glossary` and `delete_glossary`. This means your translation UI adapts to changing product names or brand guidelines without requiring a redeploy of your Vercel AI SDK application.

On-the-fly dictionary checking

The `list_source_languages` and `list_target_languages` tools let your UI display accurate language options to your users. Your Vercel AI SDK client calls these tools to build dynamic dropdown selectors. This prevents users from selecting unsupported language pairs. You can also query `get_glossary_entries` to display active translation rules directly in your admin dashboard. This setup ensures that your frontend stays in sync with your translation database without hardcoding static language arrays.

Setup guide

Set up DeepL MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all DeepL tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent DeepL transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` pointing to the Vinkius endpoint. Pass the tools returned by `mcpClient.tools()` into `streamText` to let your agent call `translate_text` and output results directly to your React components.

Yes. Your agent can call `translate_with_glossary` by referencing glossary IDs found via `list_glossaries`. This lets your Vercel AI SDK application enforce brand-specific terms during live translation streams.

Your agent chooses between `translate_formal` and `translate_informal` based on the system prompt you configure. Pass these tools to your model configuration so it selects the correct tone dynamically during runtime.

Always call `mcpClient.close()` once your translation tasks are complete. This prevents hanging HTTP connections in your serverless or Edge environment, keeping your resource usage within Vercel's limits.

Yes. All raw text strings sent to `translate_text` pass through Vinkius's ephemeral V8 Isolate Sandbox. Your translation payloads are processed in a zero-trust environment and are never cached or logged on Vinkius servers.

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