How do I find my DeepL API Key?

Log in to your [**DeepL account**](https://www.deepl.com/pro-account/plan), and you will find your Authentication Key under the 'Account' tab. Copy and paste it below.

Does this work with both Free and Pro API keys?

Yes. This server automatically detects if you are using a Free key (ending in `:fx`) or a Pro key and routes requests to the correct endpoint.

Can the agent use glossaries?

Yes. You can list your existing glossaries via the `get_glossaries` tool and identify their IDs to maintain consistency in your agent-led translations.

DeepL MCP Server for Pydantic AI 9 tools — connect in under 2 minutes

Name: DeepL
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 9 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect DeepL through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to DeepL "
            "(9 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in DeepL?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

About DeepL MCP Server

Empower your AI agent to orchestrate your entire multilingual workflow with DeepL, the world's most accurate AI translator. By connecting DeepL to your agent, you transform complex translation tasks into a natural conversation. Your agent can instantly translate text between dozens of languages, audit available language pairs, and monitor API usage without you ever touching a technical dashboard. Whether you are localized content or communicating with international teams, your agent acts as a real-time linguistic bridge, ensuring your communication is always precise and professional.

Pydantic AI validates every DeepL tool response against typed schemas, catching data inconsistencies at build time. Connect 9 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Text Auditing — Translate text into target languages and retrieve detected source language metadata instantly.
Linguistic Oversight — List all supported source and target languages to maintain a clear view of translation options.
Usage Intelligence — Monitor your character count and API limits to maintain strict control over your translation budget.
Glossary Management — List and query configured translation glossaries to ensure consistent brand terminology.
Contextual Tone Control — Translate text enforcing strict formal, informal, or standard business tones instantly.
Markup Preservation — Translate HTML elements while safely preserving tag boundaries and web structure.

The DeepL MCP Server exposes 9 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect DeepL to Pydantic AI via MCP

Follow these steps to integrate the DeepL MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 9 tools from DeepL with type-safe schemas

Why Use Pydantic AI with the DeepL MCP Server

Pydantic AI provides unique advantages when paired with DeepL through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your DeepL integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your DeepL connection logic from agent behavior for testable, maintainable code

DeepL + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the DeepL MCP Server delivers measurable value.

Type-safe data pipelines: query DeepL with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple DeepL tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query DeepL and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock DeepL responses and write comprehensive agent tests

DeepL MCP Tools for Pydantic AI (9)

These 9 tools become available when you connect DeepL to Pydantic AI via MCP:

get_account_glossaries

List configured translation glossaries

get_api_usage

Get current API usage and character limit constraints

get_glossary_dictionary

Get term mapping entries for a specific glossary ID

get_source_languages

List all supported source languages for translation

get_target_languages

g., EN-US, PT-BR) that DeepL can translate TO. List all supported target languages for translation

translate_html_markup

Translate HTML elements while preserving tag structure

translate_text_formal

g., "Sie" in German, "vous" in French) suitable for business communications. Translate text using a formal/business tone

translate_text_informal

g., "du" in German, "tu" in French) suitable for casual platforms. Translate text using an informal/casual tone

translate_text_standard

Translate text into a target language using standard tone

Example Prompts for DeepL in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with DeepL immediately.

"Translate 'Hello world' into Portuguese using DeepL."

"Show me all supported target languages in DeepL."

"What is my current DeepL usage?"

Troubleshooting DeepL MCP Server with Pydantic AI

Common issues when connecting DeepL to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

DeepL + Pydantic AI FAQ

Common questions about integrating DeepL MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your DeepL MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.