How to Use the Innform MCP in Google ADK

Q: How do I set up Google ADK to query Innform data?

You install the SDK, import McpToolset with your Vinkius HTTP URL, and pass it to your LlmAgent tools list. This exposes the entire suite of endpoints to your Gemini model instantly.

Q: Can Gemini use Google ADK to filter Innform courses?

Absolutely. The model uses the listcourses tool to fetch the entire catalog and can filter or search through them using its long-context reasoning capabilities.

Q: Is it possible to limit which Innform tools the Google ADK agent can access?

Yes, you can use the toolnames filter when initializing your toolset to expose only specific endpoints. For example, you can limit your agent to listtags and listpathways while hiding sensitive learner details using this MCP Server.

Connect Gemini agents to your Innform LMS data using Google ADK and our MCP Server to run large-scale compliance analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Innform MCP to Google ADK

Create your Vinkius account to connect Innform 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 Innform with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed compliance data to Gemini using Google ADK

The `list_results` tool retrieves all student grades and completion statuses directly into your Google Cloud agent environment. This allows your Gemini model to analyze compliance trends across thousands of rows of data using its massive context window. You can combine this tool with `list_modules` to see exactly which lessons are causing the most friction for your team. The raw API response goes straight to your agent, skipping manual data prep entirely.

Map organizational hierarchies in BigQuery

The `list_departments` tool extracts your organization's departmental structure so you can align training data with your corporate directory. Google ADK lets you feed this structure directly into your enterprise data warehouse for deep analytics. By pairing this tool with `list_locations`, your agent can pinpoint which physical offices are falling behind on compliance. It gives you a clear picture of organizational health without running manual SQL joins.

Retrieve individual learner profiles on demand

The `get_learner` tool pulls specific employee records including their active courses and current progress. Your agent can call this tool whenever a user asks about their personal training status or upcoming deadlines. It works alongside `get_me` to verify who is asking for the information, ensuring your agent only displays relevant records. This keeps your internal support desk from being buried under routine training questions.

Setup guide

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

You install the SDK, import `McpToolset` with your Vinkius HTTP URL, and pass it to your `LlmAgent` tools list. This exposes the entire suite of endpoints to your Gemini model instantly.

Absolutely. The model uses the `list_courses` tool to fetch the entire catalog and can filter or search through them using its long-context reasoning capabilities.

Yes, you can use the `tool_names` filter when initializing your toolset to expose only specific endpoints. For example, you can limit your agent to `list_tags` and `list_pathways` while hiding sensitive learner details using this MCP Server.

No, this server relies on active polling. Your agent will call tools like `list_results` on a schedule or in response to user queries to get the latest data.

All communication with the Innform API goes through an ephemeral MCP sandbox that handles your tokens securely. Your employee training records and personal identifiers are never stored on Vinkius servers or exposed to external networks.

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