How to Use the edX MCP in CrewAI

Q: How do I pass the edX MCP Server tools to a CrewAI agent?

You can pass the Vinkius HTTP endpoint directly into the mcps parameter when initializing your CrewAI agent. This automatically exposes tools like searchcourses to that specific specialized agent.

Q: Can multiple CrewAI agents share the same edX session context?

Yes. CrewAI's shared memory allows a research agent using searchprograms to hand off program IDs to an analysis agent, which then calls getprogram to extract structural details.

Q: How does CrewAI handle parallel requests to the edX catalog?

When multiple agents call getcourserun simultaneously, Vinkius handles the traffic within a highly scalable V8 sandbox. This ensures your CrewAI executions do not stall due to connection bottlenecks.

Q: How does this MCP Server secure the edX query data used by my crew?

All requests, including subject lookups via getsubjects, are executed within ephemeral isolates. Your crew's search terms, university filters, and course selections are never stored or exposed to third parties.

Coordinate cooperative agent teams to research and curate edX programs autonomously using CrewAI.

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 CrewAI

Create your Vinkius account to connect edX to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent edX research crews

The `search_courses` tool allows your specialized CrewAI research agent to crawl the edX index for specific academic topics. Once the research agent gathers the initial list, it passes the course keys to a curriculum designer agent via shared memory. The designer agent then executes `get_course` to analyze syllabus prerequisites and estimated effort. Because CrewAI supports hierarchical execution, a supervisor agent coordinates these tool calls to prevent redundant queries.

Autonomous program auditing via this MCP Server

The `search_programs` tool retrieves high-level tracks like MicroMasters and Professional Certificates for analysis by your CrewAI agents. A verification agent can then take these program structures and run `get_course_runs` to verify which specific cohorts are open for enrollment. This multi-agent coordination ensures that your final curated list contains only active, upcoming runs. The entire process runs autonomously, allowing your team to generate up-to-date educational guides without manual verification.

Automated academic taxonomy mapping in CrewAI

The `get_subjects` tool pulls the complete list of academic disciplines and course counts directly from the edX platform. Your CrewAI taxonomy agent uses this data to classify incoming course leads before a writer agent drafts the program summaries. Simultaneously, an institution specialist agent runs `get_organizations` to match courses with their respective universities like Harvard or MIT. This collaborative pipeline ensures your educational database remains accurate and properly categorized.

Setup guide

Set up edX MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke edX tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="edX Analyst",
    goal="Access and analyze edX data via MCP.",
    backstory="Expert analyst with direct edX access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent edX transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="edX Analyst",
        goal="Access and analyze edX data via MCP.",
        backstory="Expert analyst with direct edX access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent edX transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You can pass the Vinkius HTTP endpoint directly into the `mcps` parameter when initializing your CrewAI agent. This automatically exposes tools like `search_courses` to that specific specialized agent.

Yes. CrewAI's shared memory allows a research agent using `search_programs` to hand off program IDs to an analysis agent, which then calls `get_program` to extract structural details.

When multiple agents call `get_course_run` simultaneously, Vinkius handles the traffic within a highly scalable V8 sandbox. This ensures your CrewAI executions do not stall due to connection bottlenecks.

No. Vinkius hosts the server, so your CrewAI Python environment only needs to point to the secure HTTP or SSE endpoint provided in your dashboard.

All requests, including subject lookups via `get_subjects`, are executed within ephemeral isolates. Your crew's search terms, university filters, and course selections are never stored or exposed to third parties.

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