How to Use the Degreed MCP in OpenAI Agents SDK

Let your OpenAI Agents SDK run guardrails over Degreed catalog searches and skill tracking.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Degreed MCP to OpenAI Agents SDK

Create your Vinkius account to connect Degreed to OpenAI Agents SDK 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 Degreed with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe skill mapping with OpenAI Agents SDK

This integration lets your OpenAI agents pull organizational skills directly from your taxonomy. By using `list_defined_skills` and `get_user_profile`, your agent reads employee skill ratings and matches them against company standards. The OpenAI dashboard monitors these calls, so you see exactly how the agent evaluates talent profiles. Guardrails in the SDK prevent the agent from making unauthorized calls to sensitive user endpoints. When the agent queries `list_degreed_users`, the SDK validates the payload before execution. This keeps your internal employee directory secure while allowing the agent to map skills to specific user profiles.

Multi-agent learning path curation via MCP Server

Split the work between a search agent and a curation agent using built-in SDK handoffs. The search agent scans your content catalog using `search_learning_catalog` and `list_learning_content` to find relevant courses. Once it gathers raw links, it passes the data to the curation agent to build a custom learning plan. This multi-agent setup relies on the MCP Server to fetch live course durations and skill tags via `get_content_details`. The curation agent then uses `list_learning_pathways` to fit these courses into existing company learning tracks. You get clean, multi-step agent execution with full tracing on your OpenAI dashboard.

Automated completion audits with tracing

Track who is learning what by pointing your OpenAI agents at user completion histories. The agent calls `list_active_learners` to find active employees and then runs `list_user_completions` to pull their finished courses. Every single tool execution is logged in your OpenAI telemetry. If an employee falls behind on their targets, the agent references `list_learning_plans` to check their deadlines. Because the OpenAI Agents SDK manages the state, your agent can flag overdue goals and suggest matching content without losing context.

Setup guide

Set up Degreed MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Degreed tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Degreed tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Degreed tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Degreed Agent",
            instructions="You have access to Degreed tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Degreed. 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 Degreed 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 Degreed MCP in OpenAI Agents SDK

Install the SDK and instantiate the streamable HTTP client with your Vinkius endpoint. Pass this server instance in the server list when initializing your agent. The OpenAI Agents SDK automatically registers all ten Degreed tools without manual schema mapping.

Yes. You can write validation hooks in Python to inspect arguments before the SDK executes Degreed MCP tools like list_degreed_users or get_user_profile. This prevents your agent from accessing restricted employee profiles even if it attempts to call the tool.

You define two specialized agents, one for searching the catalog and another for structuring plans. The SDK allows the search agent to hand off its findings to the planning agent, which then runs list_learning_plans to update user profiles.

Yes, you can set the cache flag to true in your connection parameters. This keeps the OpenAI Agents SDK from fetching the schema from the server on every turn, reducing latency during catalog searches.

All completion data, skill ratings, and user profiles stay inside a secure V8 isolate sandbox. Vinkius handles the authentication tokens directly, so your raw credentials never touch the OpenAI Agents SDK client or logs.

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