How to Use the Degreed MCP in AutoGen

Q: How do I configure the Degreed MCP Server in AutoGen?

Install the autogen-extmcp package. Initialize your tools using mcpservertools with the Vinkius URL, and pass the resulting list into your AssistantAgent.

Deploy AutoGen agents that debate training requirements and negotiate Degreed skill assignments automatically.

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 AutoGen

Create your Vinkius account to connect Degreed to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Talent Mapping via MCP Server

Finding the right people for a project requires looking at multiple variables through this integration. You can spin up two AutoGen agents: one focused on technical requirements and another on availability. They use `list_defined_skills` to establish the baseline competencies needed for the job. The technical agent pulls `get_user_profile` to check specific skill ratings, while the availability agent looks at `list_learning_plans` to see who is already bogged down with training. They debate the tradeoffs and agree on the best candidate.

Automate Course Curation Debates

Picking the right training material shouldn't fall on one person. Set up a curriculum agent that runs `search_learning_catalog` to find options, and a compliance agent that verifies the source. The curriculum agent might push for a quick video, but the compliance agent checks `get_content_details` and flags that it lacks the required skill tags. They argue back and forth until they find a course that satisfies both duration limits and corporate standards.

Track and Verify Completion Claims

People say they finished their training, but the system often disagrees. An audit agent can use `list_active_learners` to pull the recent batch of completions from the workspace. If a discrepancy pops up, a verification agent steps in. It runs `list_user_completions` to check the exact timestamps. The two agents compare notes, resolve the conflict, and output a final verified list for HR.

Setup guide

Set up Degreed MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Degreed tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Degreed_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Degreed data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Degreed_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Degreed data")
    print(result.messages[-1].content)

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 AutoGen

Install the `autogen-ext[mcp]` package. Initialize your tools using `mcp_server_tools` with the Vinkius URL, and pass the resulting list into your `AssistantAgent`.

They take turns based on the conversation flow. One agent might pull the user list, then pass the IDs to another agent to check individual profiles.

It handles ambiguity. If a search returns too many courses, your agents can negotiate the filtering criteria and refine the query before presenting the final options.

Yes. The adapter converts the API schema automatically. Your agents read the descriptions from the taxonomy endpoint and understand exactly what each competency means.

We rely on a zero-trust architecture. When your agents debate target completion dates or linked competencies, the data passes through an isolated sandbox that destroys itself after the task finishes.

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