How to Use the 360Learning MCP in Pydantic AI

Build type-safe training workflows for 360Learning using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect 360Learning MCP to Pydantic AI

Create your Vinkius account to connect 360Learning 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 360Learning with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe user management

The `create_user` tool validates your input against strict Pydantic schemas before the platform receives the request. This prevents malformed data from hitting your 360Learning instance. If the API returns an unexpected structure, the agent throws a validation error immediately. You catch issues before they break your downstream processes.

Validating 360Learning analytics

Use `get_stats` to fetch completion data, which the framework verifies against your defined models. You get clean, typed data in every response. This removes the risk of silent corruption in your reporting logic. Your agent works with data that is guaranteed to match your schema.

Catalog oversight in Pydantic AI

Query `list_courses` to retrieve your training catalog, then verify the results with `get_course` details. The framework ensures every course ID and lesson overview adheres to your constraints. It turns your training data into a reliable, typed input for your agent. You stop guessing what the API might return and start building with confidence.

Setup guide

Set up 360Learning 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": {
        "360learning-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to 360Learning tools.",
)

result = await agent.run("List recent 360Learning 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 360Learning. 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 360Learning 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 360Learning MCP in Pydantic AI

Every MCP call is automatically validated at runtime. If the 360Learning platform returns data that doesn't fit your schema, the agent stops execution rather than hallucinating a result.

Install the slim package and pass the MCPToolset to your agent. The setup is straightforward and keeps your code strictly typed.

The server operates behind a secure Vinkius endpoint, and your agent only receives validated objects. We strictly limit the scope to course metadata and learner IDs, ensuring no raw credentials are ever handled by the model.

Yes, the toolset is model-agnostic. You can switch between OpenAI, Anthropic, or local models without changing your tool definitions.

You can pass multiple toolsets into your agent definition. This allows you to combine 360Learning actions with other data sources in a single, type-safe execution flow.

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