How to Use the edX MCP in LlamaIndex

Q: How do I load the edX MCP server into LlamaIndex?

Install llama-index-tools-mcp. Use BasicMCPClient to connect, wrap it with McpToolSpec, and call totoollistasync() to pass the functions to your FunctionAgent.

Q: Can LlamaIndex agents search edX by specific universities?

Yes. The agent uses getorganizations to pull university IDs, then passes those into searchcourses to filter results for MIT or Berkeley.

Q: Does the edX MCP server work with LlamaIndex allowedtools?

Yes. You can restrict your agent to only use searchcourses and getsubjects if you want to prevent it from making deep curriculum queries.

Index LlamaIndex vector stores with live edX catalog data and course schedules.

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 LlamaIndex

Create your Vinkius account to connect edX to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build an edX MCP Server Knowledge Base

The `search_courses` tool pulls raw course data into your LlamaIndex pipeline. Instead of just answering a user's question, your agent fetches course titles, difficulty levels, and descriptions, then embeds that data directly into a local vector store. You build RAG applications that query this live index. When a user asks for Python courses, LlamaIndex doesn't hallucinate a fake MIT syllabus. It searches the indexed output from `get_course` and grounds its response in actual platform metadata.

Embed Professional Certificates

Your application calls `search_programs` to extract MicroMasters and Bootcamps. LlamaIndex takes the program titles, descriptions, and course counts and turns them into searchable documents. You can set `include_resources=True` to give your agent deeper access. Once the agent identifies a program, it uses `get_program` to pull the exact curriculum details, adding another layer of context to your semantic search index.

Query Active Course Runs

The `get_course_runs` tool lets your agent pull scheduled offerings based on a specific course key. It filters out archived classes and only indexes upcoming or current sessions. This means your RAG application knows exactly when a class starts. If a user asks what they can take this weekend, the agent queries the vector store, checks the pacing and estimated effort from `get_course`, and returns a realistic schedule.

Setup guide

Set up edX MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all edX MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to edX tools.",
)
response = await agent.run("List recent edX data")

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 LlamaIndex

Install `llama-index-tools-mcp`. Use `BasicMCPClient` to connect, wrap it with `McpToolSpec`, and call `to_tool_list_async()` to pass the functions to your `FunctionAgent`.

Yes. The agent uses `get_organizations` to pull university IDs, then passes those into `search_courses` to filter results for MIT or Berkeley.

Yes. You can restrict your agent to only use `search_courses` and `get_subjects` if you want to prevent it from making deep curriculum queries.

It converts the JSON responses into Document objects. Those documents get embedded and stored in your vector database for semantic retrieval.

The server only processes public catalog requests like subject lists and course prerequisites. Vinkius runs this connection in a zero-trust sandbox. The MCP protocol simply passes the query and returns the catalog JSON; it retains zero memory of your application's vector indexes.

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