How to Use the Credly MCP in AutoGen

Q: How can I make one AutoGen agent responsible for all Credly API calls?

You create a dedicated AssistantAgent and give it only the Credly tools from the MCP server. Then, you instruct your other agents to delegate tasks like "list all badge templates" to that specialist agent. It's a standard and effective pattern for organizing AutoGen conversations.

Q: Can an AutoGen agent monitor Credly issuance and another approve it?

Yes, that's a perfect use case. One agent can use listissuedbadges to watch for new activity. When it finds a new badge, it can present the details to a human-in-the-loop or a second "Manager" agent for approval before taking the next step.

Q: What's the best way to get Credly tools into my AutoGen agents?

Install the autogen-extmcp package and use the mcpservertools function. You just pass it your Vinkius server URL, and it returns a list of callable tools that you can add directly to your AssistantAgent's configuration.

Let your AutoGen agents debate and manage Credly badge operations as a team.

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 AutoGen

Create your Vinkius account to connect Credly 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 Credly with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Badge Criteria

Set up a conversation between multiple AutoGen agents to design a new badge. One agent, the "Proposer," outlines the criteria. Another agent, the "Auditor," uses `list_badge_skills` and `list_badge_templates` to check if the new badge overlaps with any existing ones. They'll go back and forth, refining the idea before anyone does any real work. The Credly tools from the MCP server provide the ground truth for their debate, which prevents them from creating confusing or duplicate badges.

Build Reports Collaboratively

Task a team of agents with creating a quarterly skills report. A "Data-Gatherer" agent uses `list_issued_badges` and `get_badge_details` to pull all the raw data from Credly. A second "Analyst" agent looks at the output to find trends. Finally, a "Writer" agent drafts the report based on the Analyst's findings. This setup breaks a complex reporting task into small, manageable pieces, with each agent using the Credly tools for its specific job.

A Consensus-Driven MCP Server

This server gives your AutoGen agents a shared set of facts to work with. When one agent calls `list_org_members`, the result is posted right into the conversation. This allows other agents to see the data, verify it, and challenge the first agent's conclusions. Because AutoGen agents work by convincing each other, having a reliable source of truth is non-negotiable. This server prevents them from arguing based on bad information, which leads to better, more reliable outcomes from your multi-agent system.

Setup guide

Set up Credly 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 Credly 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="Credly_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Credly 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="Credly_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Credly 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 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 AutoGen

You create a dedicated `AssistantAgent` and give it only the Credly tools from the MCP server. Then, you instruct your other agents to delegate tasks like "list all badge templates" to that specialist agent. It's a standard and effective pattern for organizing AutoGen conversations.

Yes, that's a perfect use case. One agent can use `list_issued_badges` to watch for new activity. When it finds a new badge, it can present the details to a human-in-the-loop or a second "Manager" agent for approval before taking the next step.

Install the `autogen-ext[mcp]` package and use the `mcp_server_tools` function. You just pass it your Vinkius server URL, and it returns a list of callable tools that you can add directly to your `AssistantAgent`'s configuration.

This server turns raw API calls into functions that AutoGen agents can understand and discuss. The `McpToolAdapter` handles converting the API schema into a format the agents can use, so they can argue about *what* to do, not how to format a JSON request.

The MCP server fetches data like member lists from Credly and passes it directly to your AutoGen agent group. The data then exists inside your agent conversation's context. The Vinkius server doesn't hold on to this data after the request is finished.

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