How to Use the LearningSuite MCP in Google ADK

Q: How do I set up the LearningSuite MCP Server toolset inside the Google ADK?

Use the McpToolset class with the streamable HTTP server parameters pointing to your Vinkius endpoint. Pass this toolset directly into your LlmAgent initialization block.

Q: Can I filter which LearningSuite tools are exposed to Google ADK?

Yes, the McpToolset constructor accepts an optional toolnames list. You can limit exposure to just listcourses and getcourse to keep the agent focused.

Q: How does Gemini use the 1M+ token context window with this server?

The agent can ingest entire community feeds from listcommunityposts and synthesize them without hitting context limits, making community management painless.

Connect Google ADK to your LearningSuite MCP Server to run deep training analytics over massive contexts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LearningSuite MCP to Google ADK

Create your Vinkius account to connect LearningSuite 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 LearningSuite with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context reasoning over entire course catalogs

The Google ADK toolset connects Gemini directly to `list_courses` and `get_course` to process thousands of pages of training material in a single turn. You don't need to chunk your curriculum. The agent pulls entire modules using `get_hub` and analyzes student performance trends over long timelines. It handles the volume without losing track of details.

Sync LearningSuite data with BigQuery via Google ADK

This MCP Server integration lets your agent call `list_members` and export user progress tables straight to Google Cloud storage. You can cross-reference training metrics with actual HR performance logs. By combining `get_member` with your enterprise data warehouse, your agent generates deep reports on how course completion correlates with team output.

Manage community interactions at scale

Your agent uses `list_community_posts` and `get_community_post` to flag unanswered questions across your learning hubs. It helps community managers stay on top of student discussions. The agent can also check `list_ai_agents` and `get_ai_agent` to coordinate automated responses to common student hurdles, keeping engagement high.

Setup guide

Set up LearningSuite 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 LearningSuite 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="LearningSuite_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LearningSuite 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 LearningSuite. 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 LearningSuite 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 LearningSuite MCP in Google ADK

Use the `McpToolset` class with the streamable HTTP server parameters pointing to your Vinkius endpoint. Pass this toolset directly into your `LlmAgent` initialization block.

Yes, the `McpToolset` constructor accepts an optional `tool_names` list. You can limit exposure to just `list_courses` and `get_course` to keep the agent focused.

It does. While Stdio works for local debugging, you should use the HTTP transport for production agents deployed on Google Cloud Run.

The agent can ingest entire community feeds from `list_community_posts` and synthesize them without hitting context limits, making community management painless.

All queries run through a zero-trust, ephemeral Vinkius sandbox that processes data in memory without caching it. Your training content and user posts remain private to your Google Cloud environment.

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