How to Use the AcademyOcean MCP in LlamaIndex

Q: How do I convert AcademyOcean data into LlamaIndex documents?

You connect the MCP server using BasicMCPClient and wrap it in McpToolSpec. The output from listcourses or listlearners is parsed directly into Document objects for indexing.

Q: Can LlamaIndex query AcademyOcean progress metrics in real time?

Yes, the getlearnerprogress tool fetches live completion data during query execution. The agent calls this tool to ground its responses in current student performance.

Q: Can I filter which tools the index can access?

Yes, the MCP connector library supports an allowedtools filter. You can restrict your agent to only read tools like listcourses and block modification tools.

Q: How does the server protect student names and progress percentages?

All data retrieved via listlearners and progress tools passes through an ephemeral V8 sandbox. We never write this student information to disk, keeping your corporate training records isolated.

Index your AcademyOcean training data into LlamaIndex vector stores for instant semantic search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AcademyOcean MCP to LlamaIndex

Create your Vinkius account to connect AcademyOcean 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 AcademyOcean with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index course catalogs for RAG pipelines

The `list_courses` tool pulls your entire AcademyOcean syllabus directly into your LlamaIndex data ingestion pipeline. Your agent indexes these course titles and descriptions into a vector database for semantic search. Users can query their available training options using natural language. Instead of browsing menus, the LlamaIndex query engine matches their search intent to the indexed course list and returns the best fits.

Ground agent answers in actual learner progress

The `get_learner_progress` tool retrieves live completion stats to ground your RAG applications in hard facts. This prevents the LLM from hallucinating training achievements or missing incomplete modules. By loading these metrics into a local index, your agent answers questions about team compliance with absolute accuracy. The system checks the actual numbers before drafting status reports.

Build an AcademyOcean MCP Server search index

The `list_learners` tool exports your user directory so LlamaIndex can build a queryable search index of your student base. You can quickly map progress metrics to specific departments or cohorts. This integration lets you query your LMS data using natural language. The agent translates a prompt like who is struggling with security compliance into structured tool calls and finds the matching learners.

Setup guide

Set up AcademyOcean 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 AcademyOcean 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 AcademyOcean tools.",
)
response = await agent.run("List recent AcademyOcean 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 AcademyOcean. 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 AcademyOcean 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 AcademyOcean MCP in LlamaIndex

You connect the MCP server using `BasicMCPClient` and wrap it in `McpToolSpec`. The output from `list_courses` or `list_learners` is parsed directly into Document objects for indexing.

Yes, the `get_learner_progress` tool fetches live completion data during query execution. The agent calls this tool to ground its responses in current student performance.

You pass the tool list generated by McpToolSpec into a FunctionAgent. The agent then decides when to call `invite_learner` or list courses based on the user's prompt.

Yes, the MCP connector library supports an allowed_tools filter. You can restrict your agent to only read tools like `list_courses` and block modification tools.

All data retrieved via `list_learners` and progress tools passes through an ephemeral V8 sandbox. We never write this student information to disk, keeping your corporate training records isolated.

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