How to Use the Innform MCP in OpenAI Agents SDK

Q: How do I connect the Innform MCP Server to my OpenAI Agents SDK?

Install the package and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance inside the mcpservers list when instantiating your OpenAI agent. The agent then auto-discovers all nine user and assignment tools.

Q: Can my OpenAI Agents SDK agent automatically freeze inactive users in Innform?

Yes, your agent can call freezeuser based on custom logic you define in Python. You can write a script that checks overdue training first, then triggers the freeze if they exceed your grace period.

Q: How does the OpenAI Agents SDK handle tool discovery for Innform tools?

Set cacheToolsList=True in your server parameters to speed up discovery. The SDK queries the Vinkius endpoint once, caches the tool schemas, and lets your agent call listcompletedassignments or listusers instantly.

Control your Innform LMS directly from your OpenAI Agents SDK pipelines to automate team training and user access.

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 OpenAI Agents SDK

Create your Vinkius account to connect Innform to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Sync team changes using the Innform MCP Server

This MCP Server exposes `invite_user` and `update_user` directly to your OpenAI agents for automated onboarding. When a new hire joins, your agent triggers the invite flow, gets confirmation, and updates their profile details without human intervention. If someone leaves or takes a leave of absence, the agent uses `freeze_user` and `unfreeze_user` to manage access. Your agents handle these state changes asynchronously while logging every transaction to your OpenAI tracing dashboard.

Track training metrics with OpenAI Agents SDK guardrails

Your agent uses `list_overdue_assignments` to detect team members who missed compliance deadlines. The OpenAI Agents SDK applies built-in guardrails to verify the agent's action before it sends out reminders or escalates the issue to HR. By calling `list_completed_assignments`, the agent builds compliance reports. You set up validation rules in your Python code so the agent never pulls data for the wrong learner group or updates records without proper authorization.

Organize learners using OpenAI Agents SDK handoffs

Specialized agents use `list_groups` to segment your workforce into targeted training cohorts. One agent identifies the cohort structure, then hands off the task to another agent that uses `get_user_details` to verify individual profiles. The agent loops through your user roster with `list_users` to ensure no learner is left out of their assigned track. This multi-agent handoff pattern keeps your training pipelines clean and avoids token bloat during large runs.

Setup guide

Set up Innform MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Innform tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Innform tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Innform tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Innform Agent",
            instructions="You have access to Innform tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your OpenAI agent. The agent then auto-discovers all nine user and assignment tools.

Yes, your agent can call `freeze_user` based on custom logic you define in Python. You can write a script that checks overdue training first, then triggers the freeze if they exceed your grace period.

Set `cacheToolsList=True` in your server parameters to speed up discovery. The SDK queries the Vinkius endpoint once, caches the tool schemas, and lets your agent call `list_completed_assignments` or `list_users` instantly.

You control tool access by defining strict system instructions and guardrails in the Agent constructor. This prevents the agent from running destructive tools like `freeze_user` while still allowing it to query `list_completed_assignments` for reporting.

The MCP integration channels all user emails and names through Vinkius's secure, ephemeral sandbox. This setup handles authentication with a single token, meaning your sensitive learner details and profile metadata are never exposed or stored persistently.

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