How to Use the Credly MCP in LangChain

Build autonomous LangChain agents that manage Credly badges and track issuance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Credly MCP to LangChain

Create your Vinkius account to connect Credly 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 Credly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Badge Audits

Build a chain that uses `list_issued_badges` to get a full list of what's been sent out. For any badge that looks off, your agent can automatically pull details with `get_badge_details` to check for compliance against your rules. This isn't a simple script that just pulls data. It's a reasoning loop. Your LangChain agent decides which badges need a closer look and chains together the right tools to investigate, flagging problems without you lifting a finger.

Chain Together Credly Reports

Create a multi-step agent that does real reporting work. Have it start by pulling all available badge templates using `list_badge_templates`. Then, for a specific template, it can find every single recipient with `list_badge_recipients`. Your LangChain agent holds the context between these calls. It connects different pieces of information from the Credly system into one coherent report. You define the goal, and the agent figures out the steps.

The Credly MCP Server

This isn't an API wrapper. It's a managed MCP server that turns Credly actions into composable tools for LangChain. Your agent gets a clean list of functions—`list_org_members`, `list_authorized_issuers`—without you writing a line of boilerplate code. Vinkius handles the authentication, scaling, and all the annoying parts of infrastructure. You just get a URL, connect your agent, and focus on its logic. It's the fastest way to get a smart agent working with your Credly data.

Setup guide

Set up Credly 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 Credly 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({
    "credly-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 Credly 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 Credly. 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 Credly 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 Credly MCP in LangChain

You get the tools from the client and pass them straight to the `create_agent` function. The agent sees the tool names and descriptions, like `get_badge_details`, and decides when to call them based on its prompt. This lets the agent reason about how to use your Credly account.

Yes, that's exactly what LangChain is for. You can create a chain that first calls `list_badge_recipients` from this MCP server, then uses that list of people to query your company's HR database. The framework is built for mixing tools from different sources.

Of course. If you connect LangSmith, every call to a Credly tool shows up in your trace. You'll see the exact inputs and outputs for tools like `list_badge_skills`, which is critical for debugging your agent's decisions.

Vinkius manages it. You get one endpoint token when you subscribe to the server. Your LangChain client uses that token for all requests to the Credly server, so you don't have to build and maintain an OAuth flow.

The server only processes data in transit. When your LangChain agent calls `get_badge_details`, the server proxies that request to Credly and returns the response. No badge recipient data or organization info is ever stored on Vinkius servers.

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