How to Use the Moodle MCP in CrewAI

Q: How do I connect the Moodle MCP Server to a CrewAI agent?

Pass your Vinkius server URL directly into the agent's mcps parameter during initialization. For more control, use MCPServerHTTP from crewai.mcp to filter which tools like getusergrades the agent can access.

Q: Can CrewAI agents collaborate to build a Moodle course?

Yes, one agent can use listcategories to find the right department, while another executes createcourses to build the shell. This collaborative workflow ensures your courses are organized correctly from the start.

Q: Can I limit which tools an agent can use?

Yes, you can use the toolfilter option in MCPServerHTTP to restrict access. For example, you can allow a support agent to use listassignments while blocking them from using createusers.

Run specialized CrewAI agent teams to coordinate Moodle course creation, student grading, and active monitoring.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Moodle MCP to CrewAI

Create your Vinkius account to connect Moodle 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 Moodle with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent Moodle operations with CrewAI

The `list_courses` tool allows your agent crew to map out your entire active curriculum. In CrewAI, you don't rely on a single agent to do everything; instead, a researcher agent lists the courses while a moderator agent uses `get_enrolled_users` to audit student rosters. This division of labor keeps your LMS organized and prevents administrative errors. You configure this by passing the MCP Server endpoint directly into your CrewAI agent's `mcps` array. The agents share a common memory space, meaning the coordinator agent knows exactly which courses need attention based on the auditor's findings. It makes complex LMS management completely autonomous.

Autonomous course auditing using this MCP Server

The `get_course_contents` tool exposes syllabus details to your specialized agent crew. A curriculum analyst agent can review these contents to ensure they match university standards, while a separate files agent uses `list_files` to flag outdated PDFs. They work in parallel, combining their findings into a single report. This team-based approach handles massive LMS sites without breaking a sweat. You don't have to write custom scraping scripts or click through hundreds of pages manually. The crew crawls the course structure and reports back only when it finds inconsistencies.

Automated grade monitoring and student outreach

The `get_user_grades` tool provides the data your agent crew needs to track student progress. One agent acts as the data analyst, pulling grades and identifying students who are falling behind on assignments. A second agent, specialized in student support, uses `list_assignments` to draft personalized study plans based on the missing work. This division of labor ensures that outreach is highly targeted and contextual. The support agent never sees raw database credentials, only the specific metrics passed by the analyst agent. It is a highly efficient way to scale student support without burning out your staff.

Setup guide

Set up Moodle 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 Moodle tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Moodle 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="Moodle Analyst",
        goal="Access and analyze Moodle data via MCP.",
        backstory="Expert analyst with direct Moodle access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Moodle 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 Moodle. 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 Moodle 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 Moodle MCP in CrewAI

Pass your Vinkius server URL directly into the agent's `mcps` parameter during initialization. For more control, use `MCPServerHTTP` from `crewai.mcp` to filter which tools like `get_user_grades` the agent can access.

Yes, one agent can use `list_categories` to find the right department, while another executes `create_courses` to build the shell. This collaborative workflow ensures your courses are organized correctly from the start.

CrewAI schedules agent tasks sequentially or hierarchically. This prevents your agents from spamming tools like `list_users` simultaneously, protecting your LMS database from performance spikes.

Yes, you can use the `tool_filter` option in `MCPServerHTTP` to restrict access. For example, you can allow a support agent to use `list_assignments` while blocking them from using `create_users`.

Absolutely. Your student names and emails are processed dynamically in memory and never stored. Vinkius runs the MCP Server in an ephemeral, zero-trust sandbox, keeping your LMS data safe from leaks.

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