How to Use the Duolingo MCP in Pydantic AI

Q: How do I connect the Duolingo MCP Server to Pydantic AI?

Use the unified MCPToolset constructor pointing to your Vinkius HTTP URL. Pass this toolset directly to your Pydantic AI Agent to start querying profile data.

Q: Does this Duolingo toolset support the older MCPServerHTTP class?

No, that class is deprecated. You should use the unified MCPToolset class for all HTTP and SSE transport connections.

Force type-safe validation on Duolingo profile metrics and leaderboard stats using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duolingo MCP to Pydantic AI

Create your Vinkius account to connect Duolingo 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 Duolingo with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Duolingo Profiles in Pydantic AI

`get_user_by_username` and `get_user_by_id` fetch raw Duolingo profile data, which Pydantic AI immediately validates against strict schema definitions. If the profile payload contains unexpected fields, your agent fails loudly. This prevents your application from processing corrupted data. This strict validation ensures that streak counts and XP totals are always parsed as integers. You can confidently pass these validated metrics to your downstream application logic. It works every single time.

Query Type-Safe Translation Hints via MCP Server

`get_dictionary_hints` returns Duolingo translation pairs that are strictly typed before they reach your LLM. Your Pydantic AI agent uses these validated tokens to guarantee that translation data matches your exact model structure. No more random type errors in production. Because this MCP Server runs externally, you connect to it using the unified HTTP toolset. The framework handles the transport while Vinkius secures the connection. You get type safety without the configuration headache.

Track Leaderboards with Pydantic AI

`get_daily_leaderboard` and `get_leaderboard` fetch real-time Duolingo XP rankings and tier positions. Your Pydantic AI agent validates these standings, ensuring you never pass malformed ranking arrays to your user interface. It keeps your dashboard clean. You can also pull social statistics using `get_friends` to compare active streaks. If a friend's profile is set to private, the validation layer safely catches the missing fields. Your app won't crash.

Setup guide

Set up Duolingo 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": {
        "duolingo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Duolingo 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 Duolingo. 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 Duolingo 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 Duolingo MCP in Pydantic AI

Use the unified `MCPToolset` constructor pointing to your Vinkius HTTP URL. Pass this toolset directly to your Pydantic AI Agent to start querying profile data.

Your Pydantic AI agent will raise a validation error instantly. This prevents your application from silently processing corrupted profile or leaderboard data.

Yes. The toolset is completely model-agnostic, allowing your Pydantic AI agent to run validation checks whether you use OpenAI, Anthropic, or local LLMs.

No, that class is deprecated. You should use the unified `MCPToolset` class for all HTTP and SSE transport connections.

Your API keys and profile metrics are isolated inside a zero-trust V8 sandbox. Pydantic AI queries the server over an encrypted channel, and Vinkius rotates transport keys automatically to prevent credential exposure.

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