How to Use the Duolingo MCP in Google ADK

Q: How do I import Duolingo data into Google ADK?

Instantiate McpToolset with your Vinkius HTTP URL and pass it to your LlmAgent. Your Google ADK agent immediately gains access to all 8 profile and leaderboard tools.

Q: Can Gemini use Duolingo translation hints in Google ADK?

Yes. Your agent can call getdictionaryhints to fetch real-time translation pairs, which Gemini uses to ground its language-learning responses.

Q: How do I restrict my agent to only see Duolingo leaderboard tools?

Use the toolnames parameter in your ADK toolset configuration. Specify only the tools you want, like the daily leaderboard endpoint, to keep your agent focused.

Feed Duolingo leaderboard and profile data into your Google ADK pipelines for long-context Gemini analytics.

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 Google ADK

Create your Vinkius account to connect Duolingo to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze Duolingo Streaks with Google ADK

`get_user_by_username` and `get_user_by_id` pull complete Duolingo profile statistics, including streaks and total XP, directly into your Google ADK agent. This lets your Gemini models analyze long-term learning patterns over hundreds of previous sessions. It's built for deep analysis. You can feed this raw profile data directly into BigQuery tables. The Google ADK agent uses these statistics to run predictive models on user churn. You get real data instead of vague guesses.

Run Multi-Language Queries with this MCP Server

`get_dictionary_hints` and `get_version_info` allow your Google ADK agent to resolve Duolingo translation pairs and check supported language codes. This setup gives your Gemini model the exact vocabulary data it needs to build custom translation pipelines. It handles complex multi-language tasks easily. The underlying MCP Server runs in a zero-trust sandbox, keeping your translation queries isolated. You can restrict which tools are exposed to the Google ADK agent using the built-in tool filter. This keeps your enterprise pipelines clean.

Export Friend Lists using Google ADK

`get_friends` and `get_leaderboard` extract Duolingo social connections, XP totals, and tier rankings for any public profile. Your Google ADK agent can process these large friend networks within Gemini's million-token context window. It handles massive datasets without breaking a sweat. The agent maps these social structures to identify top-performing cohorts. All of this happens over a secure stream, using a single MCP Server connection token managed by Vinkius.

Setup guide

Set up Duolingo MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Duolingo tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Duolingo_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Duolingo tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate `McpToolset` with your Vinkius HTTP URL and pass it to your `LlmAgent`. Your Google ADK agent immediately gains access to all 8 profile and leaderboard tools.

Yes. Your agent can call `get_dictionary_hints` to fetch real-time translation pairs, which Gemini uses to ground its language-learning responses.

Yes, this server supports both Stdio and HTTP transports. You can configure the Google ADK toolset to use either protocol depending on your hosting environment.

Use the `tool_names` parameter in your ADK toolset configuration. Specify only the tools you want, like the daily leaderboard endpoint, to keep your agent focused.

Your friends list and XP rankings never touch persistent storage on our servers. Vinkius executes each MCP Server request in an ephemeral V8 sandbox that is destroyed immediately after Google ADK receives the payload.

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