How to Use the Degreed MCP in LangChain

Q: How do I connect the Degreed MCP Server to LangChain?

Install langchain-mcp-adapters. Initialize a MultiServerMCPClient pointing to your Vinkius endpoint, then pass the tools from client.gettools() into your ReAct agent.

Q: Can LangChain track progress across multiple Degreed users?

Yes. Your agent can call listactivelearners and iterate through the results. It maintains context across multiple tool calls to build a complete picture of team progress.

Q: Does LangSmith track these tool calls?

Every API hit gets logged. You can see exactly how long searchlearningcatalog took to run and what parameters your agent passed.

Connect Degreed to your LangChain agents to build learning pathways and track skill progression 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 LangChain

Create your Vinkius account to connect Degreed to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Skills Across Org with the Degreed MCP Server

LangChain agents excel at multi-step reasoning, and now they can map your entire talent pool using this integration. Connect the server and use `list_defined_skills` to grab your company's taxonomy. Then, feed that directly into a chain that queries `list_degreed_users` to see who actually holds those competencies. You get full observability through LangSmith while this runs. Watch the token usage as your ReAct agent pulls `get_user_profile` to evaluate individual skill ratings, deciding on the fly which learning materials to assign next based on the gaps it finds.

Build Automated Learning Chains

Stop manually assigning courses. You can wire up a chain that triggers when a new project starts, using `search_learning_catalog` to find relevant materials. The agent takes those results and pipes them into a custom prompt to evaluate the best fit. Once it picks a course, the chain calls `get_content_details` to verify the duration and skill tags. With this MCP integration, you can then write a custom tool to push that assignment to Slack, letting the agent handle the entire workflow from discovery to notification.

Monitor Completion Data in Real Time

Tracking who finished what is usually a headache of CSV exports. Your LangChain agent can just run `list_active_learners` to grab a fresh list of people who recently completed their training. If a manager asks about a specific employee, the agent hits `list_user_completions`. It pulls the exact timestamps and skill points earned, formats the data into a clean summary, and drops it right into your dashboard.

Setup guide

Set up Degreed MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Degreed tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "degreed-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Degreed transactions"
    })
    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 LangChain

Install `langchain-mcp-adapters`. Initialize a `MultiServerMCPClient` pointing to your Vinkius endpoint, then pass the tools from `client.get_tools()` into your ReAct agent.

Yes. Your agent can call `list_active_learners` and iterate through the results. It maintains context across multiple tool calls to build a complete picture of team progress.

Chains let you pipe outputs directly into new inputs. You can grab a user's ID with one tool and immediately feed it into another to pull their specific learning plans.

Every API hit gets logged. You can see exactly how long `search_learning_catalog` took to run and what parameters your agent passed.

The V8 Isolate Sandbox ensures that sensitive learning histories and skill ratings from `get_user_profile` never leak. Auth tokens live only for the duration of the request, keeping employee records locked down.

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