How to Use the edX MCP in AutoGen

Q: How do I pass the edX MCP server to AutoGen agents?

Install autogen-extmcp. Call mcpservertools with your Streamable HTTP URL, and pass the resulting list into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use the edX MCP server simultaneously?

Yes. McpToolAdapter handles the schema conversions. You can give the searchcourses tool to one agent and the getcourserun tool to another.

Q: How do AutoGen agents handle missing edX prerequisites?

If an agent pulls a class via getcourse and sees missing prerequisites, it can automatically trigger a new searchcourses query to find the foundational class first.

Q: Can AutoGen track edX course statuses?

Yes. An agent can monitor getcourseruns to check if a status changes from upcoming to current, alerting the rest of the agent group.

Deploy AutoGen agents that use this MCP Server to debate edX course selections and program paths.

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 AutoGen

Create your Vinkius account to connect edX to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent edX MCP Server Discovery

Your AutoGen setup can assign `search_courses` to a dedicated research agent. This agent queries the catalog, filtering by language and subject, to build a list of potential classes. It hands that raw list over to a separate evaluation agent. The evaluation agent then calls `get_course` to pull the estimated effort and prerequisites. If the research agent suggests a class that requires 20 hours a week, the evaluation agent pushes back and requests a lighter alternative. They debate until they find a realistic match for the user.

Compare MicroMasters and Single Classes

One agent uses `search_programs` to find intensive Bootcamps and XSeries. A competing agent uses `search_courses` to find standalone alternatives. They present the user with a direct comparison of time commitments and course counts. To settle disagreements, they pull hard data. An agent triggers `get_program` to see exactly what the MicroMasters entails, while another checks `get_course_runs` to see if the standalone classes are actually available right now. The user gets a consensus recommendation.

Validate University Offerings

Your research agent calls `get_organizations` to pull the exact names and course counts for partners like IBM and Google. It uses this data to restrict its subsequent searches. If a user demands a tech-focused curriculum, the agent queries `get_subjects` to find the exact taxonomy terms. It maps those subjects to specific organizations, ensuring the final list of courses comes strictly from validated industry partners.

Setup guide

Set up edX MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes edX tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="edX_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent edX data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="edX_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent edX data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]`. Call `mcp_server_tools` with your Streamable HTTP URL, and pass the resulting list into your `AssistantAgent` constructor.

Yes. `McpToolAdapter` handles the schema conversions. You can give the `search_courses` tool to one agent and the `get_course_run` tool to another.

If an agent pulls a class via `get_course` and sees missing prerequisites, it can automatically trigger a new `search_courses` query to find the foundational class first.

Yes. An agent can monitor `get_course_runs` to check if a status changes from upcoming to current, alerting the rest of the agent group.

No. The MCP server only transmits your specific search parameters, like 'Python' or 'MIT', to fetch public syllabus and program data. Vinkius handles the authorization via a single endpoint token and destroys the container after the session, ensuring your agent's internal reasoning stays private.

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