How to Use the eduMe MCP in OpenAI Agents SDK

Q: How do I register the eduMe MCP Server with the OpenAI Agents SDK?

Instantiate the toolset using MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance inside the mcpservers list to your Agent constructor during initialization.

Q: How does the OpenAI Agents SDK handle caching for eduMe courses?

Set cacheToolsList=True in your setup configuration. This keeps the SDK from refetching tool schemas like listtrainingcourses on every agent turn, reducing latency.

Give your OpenAI Agents SDK production system direct access to mobile training records and trainee performance data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eduMe MCP to OpenAI Agents SDK

Create your Vinkius account to connect eduMe 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 eduMe with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit team progress with OpenAI Agents SDK

The `quick_team_training_audit` tool fetches high-level completion metrics and member counts for your active mobile training cohorts. Your OpenAI Agents SDK system runs this tool to verify compliance before triggering automated compliance alerts or supervisor notifications. You pass this tool directly to your agent constructor to let it check team statuses on demand. Because the agent validates actions before execution, it won't trigger external alerts unless the audit returns clear, verified training gaps.

Pull trainee profiles and history

To inspect individual progress, the `get_user_training_profile` tool retrieves the complete training history and completion status for any registered mobile worker. Your OpenAI Agents SDK uses this raw profile data to decide if a worker needs to be assigned to a new cohort. This setup prevents silent failures in your production pipelines. The agent reads the exact course completion dates, matches them against compliance deadlines, and hands off the task to a specialized assignment agent if gaps are found.

Inspect course configurations dynamically

Running the `get_course_details` tool exposes the specific module structure and settings of your mobile training modules. Your OpenAI Agents SDK queries this MCP endpoint to map which lessons a user must complete to resolve an active compliance flag. With the SDK caching tools list, your agent quickly matches user gaps against the active course catalog without hitting rate limits. Your agents always operate on real-time curriculum data, avoiding outdated course assignments.

Setup guide

Set up eduMe 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 eduMe tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate eduMe 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="eduMe Agent",
            instructions="You have access to eduMe 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 eduMe. 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 eduMe 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 eduMe MCP in OpenAI Agents SDK

Instantiate the toolset using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance inside the `mcp_servers` list to your Agent constructor during initialization.

Yes. You can write custom interceptors that inspect arguments passed to `quick_team_training_audit` before the agent runs the tool, preventing unauthorized data lookups.

Set `cacheToolsList=True` in your setup configuration. This keeps the SDK from refetching tool schemas like `list_training_courses` on every agent turn, reducing latency.

It uses streamable HTTP transport managed by Vinkius. Your python runtime connects over a secure HTTP stream, keeping the connection alive for rapid tool execution.

Vinkius runs the server in a zero-trust, ephemeral V8 Isolate sandbox. Your trainee profiles and course completion records are never stored on Vinkius servers, and all API calls require a single, secure endpoint token.

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