How to Use the DeepL MCP in Pydantic AI

Q: How do I configure DeepL with Pydantic AI?

Run pip install "pydantic-ai-slimmcp". Define your connection using MCPToolset("http://...") with your MCP Server URL and pass it to your Agent via the toolsets array.

Q: Can Pydantic AI validate DeepL target languages?

The agent pulls the exact list via gettargetlanguages. It verifies the requested dialect code against that validated array before translating.

Q: How does the system handle business translations?

You trigger translatetextformal. The API applies strict grammatical rules, like using "Sie" in German, rather than guessing based on context.

Q: Will Pydantic AI track my DeepL API usage?

It reads the exact remaining character count using getapiusage. You can write Pydantic models that block execution if the limit is too low.

Give your Pydantic AI agents strict, type-safe access to DeepL translations and corporate glossaries.

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 Pydantic AI

Create your Vinkius account to connect DeepL to Pydantic 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strict Glossary Validation

Bad translations ruin production interfaces. Forcing your agent to use `get_glossary_dictionary` ensures specific brand terms map exactly to your predefined rules via this MCP Server. Pydantic validates the exact response payload. If the API returns unexpected data from `get_account_glossaries`, your application fails loudly instead of silently corrupting your localized content.

Guaranteed DeepL MCP Tone Control

Prompting an LLM to 'act formal' rarely works consistently. Executing `translate_text_formal` guarantees business-appropriate grammar at the API level. Informal messaging follows the same pattern. Calling `translate_text_informal` handles social phrasing, while `get_target_languages` confirms the exact regional dialect code before execution.

Flawless HTML Reconstruction

One missing closing tag breaks an entire web view. The `translate_html_markup` tool processes the text nodes while treating the DOM structure as immutable. Character limits matter when processing large batches. Your agent can validate remaining capacity via `get_api_usage` before starting a massive localization job.

Setup guide

Set up DeepL MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "deepl-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to DeepL tools.",
)

result = await agent.run("List recent DeepL transactions")
print(result.output)

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 Pydantic AI

Run `pip install "pydantic-ai-slim[mcp]"`. Define your connection using `MCPToolset("http://...")` with your MCP Server URL and pass it to your Agent via the `toolsets` array.

The agent pulls the exact list via `get_target_languages`. It verifies the requested dialect code against that validated array before translating.

You trigger `translate_text_formal`. The API applies strict grammatical rules, like using "Sie" in German, rather than guessing based on context.

It reads the exact remaining character count using `get_api_usage`. You can write Pydantic models that block execution if the limit is too low.

We route your raw text and HTML payloads through an isolated, ephemeral runtime. No persistent storage exists on our end, ensuring your proprietary strings remain completely confidential.

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