How to Use the edX MCP in OpenAI Agents SDK

Q: How do I connect the edX Alternative MCP Server to the OpenAI Agents SDK?

Instantiate MCPServerStreamableHttp with our hosted endpoint URL and pass it to your Agent constructor. The SDK auto-discovers all 10 tools, including listcourses and listenrollments, with zero manual configuration.

Q: Can I use OpenAI Agents SDK guardrails with the edX Alternative tools?

Yes, you can intercept tool calls like enrollincourse before they run. This lets you write custom Python validation logic to verify student eligibility before the agent executes the enrollment.

Q: How do I optimize tool calling performance for course discovery?

Set cacheToolsList=True in your server parameters to cache the tool schemas. This reduces latency when your agent repeatedly calls listcourses and getcoursedetails to find active learning paths.

Run production-ready agent teams that manage Open edX enrollments and grades using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect edX MCP to OpenAI Agents SDK

Create your Vinkius account to connect edX to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup edX with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automated enrollment and registration guardrails

Your OpenAI agent uses `enroll_in_course` to register students directly into active tracks. By feeding this tool into your agent constructor, the SDK auto-discovers the endpoint and applies your defined safety constraints before executing the registration. You can configure specialized agents to handle student onboarding. One agent checks prerequisites with `get_user_profile` while another handles the actual sign-up, passing the state back and forth.

Deep-dive grading pipelines with trace logs

Track student performance by letting your agent call `get_user_grades` and `get_course_grades` autonomously. The OpenAI dashboard traces every call, showing you the exact inputs and outputs of each grading query. This setup lets you build grading agents that flag struggling students. Pulling course blocks via `get_course_blocks` allows the agent to identify which specific module caused the grade drop.

Manage student profiles using this MCP Server

Keep student data synchronized by exposing `update_user_profile` to your agent pool. The OpenAI Agents SDK handles the connection to the MCP Server over streamable HTTP, making the tools instantly available. Your agent reads the current state with `get_user_preferences` before making updates. This prevents overwriting user-selected settings during bulk profile updates.

Setup guide

Set up edX 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 edX tools at runtime.
3

Create your Agent

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

Run the agent

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

Instantiate `MCPServerStreamableHttp` with our hosted endpoint URL and pass it to your Agent constructor. The SDK auto-discovers all 10 tools, including `list_courses` and `list_enrollments`, with zero manual configuration.

Yes, you can intercept tool calls like `enroll_in_course` before they run. This lets you write custom Python validation logic to verify student eligibility before the agent executes the enrollment.

Yes, you can split tasks between specialized agents. For example, one agent can inspect student records using `get_user_profile` and hand off the task to a registration agent that executes `enroll_in_course`.

Set `cacheToolsList=True` in your server parameters to cache the tool schemas. This reduces latency when your agent repeatedly calls `list_courses` and `get_course_details` to find active learning paths.

Our managed gateway runs inside an isolated sandbox and never stores your student grades or profile data. Every request to `get_user_grades` passes through an encrypted, ephemeral connection that immediately discards the payload after delivery.

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