How to Use the edX MCP in Pydantic AI

Q: How can my Pydantic AI agent find all advanced edX courses from IBM?

Your agent would call the searchcourses tool. It needs to provide the arguments level='advanced' and organization='ibm'. The response will be a validated list of Pydantic objects, one for each course.

Q: Can a Pydantic AI agent confirm the start date for a specific edX course run?

Yes. After getting a courserun ID, the agent calls the getcourserun tool. The returned Pydantic object will contain the start date, which you can access as a typed attribute, like result.startdate.

Get type-safe, validated access to the edX course catalog directly within your Pydantic AI agent.

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 Pydantic AI

Create your Vinkius account to connect edX to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Search for Courses with Confidence

This MCP Server connects your Pydantic AI agent to the edX API. You can use the `search_courses` and `search_programs` tools to find classes and professional certificates. Your agent can filter by subject, level, and organization like MIT or Google. The key difference is that every response is automatically parsed into a Pydantic model. You don't get a raw JSON blob; you get a structured, type-checked object. This means no more `KeyError` exceptions if the API response changes unexpectedly.

Get Validated Course Details

The `get_course` tool fetches all the details for a specific course. Your Pydantic AI agent receives a clean object with fields for title, description, prerequisites, and more. If the edX API returns a null value for a required field, you get a `ValidationError`, not a silent bug. The same principle applies to `get_course_run`. When your agent checks for available sessions, you can trust the data structure. It's the right way to build reliable agents that don't hallucinate fields or crash on bad data.

Explore with a Pydantic MCP Server

You can build a complete picture of the edX platform. The `get_organizations` tool returns a list of partner institutions. The `get_subjects` tool gives you all the course categories. Both are, of course, backed by Pydantic models. This lets you write much more robust code. You can build functions that take these Pydantic objects as input, with full confidence that the data shape and types are correct. It makes chaining tool calls—like finding an organization, then searching its courses—much safer.

Setup guide

Set up edX MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "edx-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to edX tools.",
)

result = await agent.run("List recent edX transactions")
print(result.output)

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 Pydantic AI

Your agent would call the `search_courses` tool. It needs to provide the arguments `level='advanced'` and `organization='ibm'`. The response will be a validated list of Pydantic objects, one for each course.

While you could just try, a better way is to check the edX documentation or run a broad `search_programs` query once. The tool supports 'MicroMasters', 'Professional Certificate', 'XSeries', and 'Bootcamp'. Your Pydantic models will ensure you handle the response correctly.

Yes. After getting a `course_run` ID, the agent calls the `get_course_run` tool. The returned Pydantic object will contain the start date, which you can access as a typed attribute, like `result.start_date`.

The Pydantic AI toolset will raise an exception. The Vinkius MCP Server abstracts away transient network issues, but a persistent API error will be surfaced so your agent can handle it explicitly.

Only the search query and filter parameters, like a course subject or organization name, are sent to the server. The server never accesses your user profile or any private data. All it sees is the request for public edX catalog information.

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