How to Use the edX MCP in OpenAI Agents SDK

Q: How can my OpenAI Agent find beginner Python courses on edX?

Your agent should use the searchcourses tool. It can set the parameters q='Python' and level='beginner' to get a targeted list of courses and their details.

Q: Can an OpenAI Agent check if a specific edX course is currently running?

Yes. After finding a course with searchcourses, the agent gets a course key. It then uses getcourseruns with that key and status='current' to see if there's an active session.

Q: What's the best way to find a MicroMasters program from MIT using the OpenAI Agents SDK and this edX server?

The most direct way is to have your agent call searchprograms. It should use the parameters organization='mitx' and type='MicroMasters' to filter the results.

Connect your OpenAI Agent to the edX catalog to find courses from MIT, Harvard, and more.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect edX MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find Courses and Programs

Connect this MCP Server and your agent can immediately use `search_courses` to find classes on any topic. It can filter by subject, language, or even specific schools like Berkeley and IBM. Once it finds a course, it gets a direct enrollment link. Your agent can also look for longer-term programs. The `search_programs` tool lets it find MicroMasters and Professional Certificates. It's a simple way to have your agent map out an entire learning path, not just find one-off classes.

Get Specific Course Details

The `get_course` tool lets your agent pull everything for a single course: prerequisites, weekly effort, and pacing. This is how your agent goes from a search result to a concrete recommendation. It’s not just a title; it’s actionable data. With `get_course_run`, your agent can check for currently active or upcoming sessions. This prevents it from suggesting a course that isn't available. The OpenAI Agent framework's guardrails can even be configured to require this check before presenting an option to the user.

Explore the edX Ecosystem with your Agent

This isn't just for searching. Your agent can use `get_organizations` to list all 160+ institutions, from universities to companies. It can see which schools offer the most courses on a given topic. The `get_subjects` tool provides a full map of the edX curriculum. Before even running a search, your agent can understand the available categories, making its discovery process smarter and more targeted. It's about giving your OpenAI Agent the context to make better decisions.

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

Your agent should use the `search_courses` tool. It can set the parameters `q='Python'` and `level='beginner'` to get a targeted list of courses and their details.

Yes. After finding a course with `search_courses`, the agent gets a course key. It then uses `get_course_runs` with that key and `status='current'` to see if there's an active session.

The most direct way is to have your agent call `search_programs`. It should use the parameters `organization='mitx'` and `type='MicroMasters'` to filter the results.

No. The Vinkius MCP Server is ephemeral. Each request from your agent is stateless and we don't log the queries you make.

The server only handles public edX catalog data like course titles and descriptions. It never touches your personal edX account or user information. All connections are over HTTPS, and the Vinkius platform isolates every request.

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