How to Use the edX MCP in LangChain

Q: How do I connect the edX MCP to LangChain?

Install langchain-mcp-adapters. Initialize MultiServerMCPClient with the server URL, call client.gettools(), and bind them to your ReAct agent.

Q: Can LangChain filter edX courses by difficulty level?

Yes. The searchcourses tool accepts level parameters like beginner, intermediate, or advanced. Your agent handles the filtering natively before returning the list.

Q: Does LangSmith trace the edX tool calls?

Yes. Every time the agent triggers getcourserun, LangSmith logs the inputs, the JSON response, and the latency. You see exactly what the model saw.

Build ReAct agents in LangChain that search and filter edX courses from Harvard and MIT.

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 LangChain

Create your Vinkius account to connect edX to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain edX MCP Server Searches

Your LangChain agent hits the edX catalog directly using `search_courses`. It takes user intent, structures the query parameters, and pulls back course titles, descriptions, and enrollment links from top institutions. The agent filters out beginner classes if the user asks for advanced material. The output of that search becomes the input for the next node in your graph. Your chain passes the resulting course keys into `get_course_runs` to check if a class is currently active or archived. You get a complete, multi-step discovery pipeline that validates scheduling before recommending a class to the user.

Parse MicroMasters and Bootcamps

The `search_programs` tool lets your agent find Professional Certificates and MicroMasters based on free-text input. Instead of just scraping web pages, LangChain pulls structured JSON containing the exact course counts and program types. Once the agent identifies a relevant program, it calls `get_program` to extract the underlying curriculum. You can trace every step of this execution in LangSmith, tracking exactly how many tokens the agent burned while deciding between a bootcamp and an XSeries.

Map Subjects to Organizations

Your agent uses `get_subjects` to pull exact subject names and current course counts across the platform. It doesn't guess what categories exist. It reads the actual taxonomy before formulating a search query. You can pair this with `get_organizations` to see which partners dominate specific fields. If a user only wants Ivy League content, the agent filters the workflow to query IDs matching Harvard or Berkeley, then fetches the actual course details with `get_course`.

Setup guide

Set up edX MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes edX tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "edx-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent edX transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters`. Initialize `MultiServerMCPClient` with the server URL, call `client.get_tools()`, and bind them to your ReAct agent.

Yes. The `search_courses` tool accepts level parameters like beginner, intermediate, or advanced. Your agent handles the filtering natively before returning the list.

Direct calls require you to write the routing logic manually. A LangChain agent decides when to call `search_programs` versus `get_course` based on the conversation context, saving you from writing brittle if/then statements.

Yes. Every time the agent triggers `get_course_run`, LangSmith logs the inputs, the JSON response, and the latency. You see exactly what the model saw.

This integration reads public catalog data like course descriptions, effort estimates, and organization names. It does not touch user enrollment data or payment details. The MCP server runs ephemerally in a V8 isolate, meaning your search queries disappear the moment the connection drops.

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