How to Use the Credly MCP in CrewAI

Q: How do I give a CrewAI agent access to just one Credly tool?

Use the MCPServerHTTP class from crewai.mcp. When you initialize it, pass a toolfilter list with the exact tool names you want, like 'getbadgedetails'. Then just assign that server instance to your agent.

Q: What kind of data can I get about a specific badge?

The getbadgedetails tool gives you everything about a single issued badge. You'll see the recipient's info, the issue and expiration dates, and the specific evidence or criteria they met to earn it.

Q: Can my CrewAI agents monitor badge templates in Credly?

Yes. You can assign an agent to periodically run listbadgetemplates to watch for new or modified designs. From there, it can use gettemplatedetails to pull the full design and issuance criteria for review or logging.

Build an autonomous CrewAI team to manage your organization's digital badges and track skills on Credly.

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 CrewAI

Create your Vinkius account to connect Credly to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Badge Auditing

Give an agent the role of 'Compliance Officer'. It can use the `list_issued_badges` and `list_badge_recipients` tools to get a complete picture of who has what. If it finds something interesting, it can dig into the specifics of any badge with `get_badge_details`. This lets you build a crew that constantly monitors your badging program. Another agent can watch for changes to permissions with `list_authorized_issuers` or check for new badge designs with `list_badge_templates`. Your crew can flag anything that looks off, all without human intervention.

Map Your Org's Skills with this MCP Server

You can task a 'Talent Analyst' agent to map out your entire team's skillset. It starts by getting a full inventory of competencies using the `list_badge_skills` tool. This is how you build a real-time skills directory that never goes out of date. That agent can work with another one to map the organization itself. Use `list_org_members` to see who's on the team and `list_connected_organizations` to see how you're connected to partners. The crew can then pull specifics on any of them with `get_organization_info` to build reports or update internal systems automatically.

Get Your Crew Running in Minutes

Connecting your CrewAI agents is simple. Just pass the Vinkius MCP endpoint URL into an Agent's `mcps` list. That's it. Your crew gets instant access to all the Credly tools, no extra code or complex setup required. For more advanced crews, you can use the `MCPServerHTTP` class from `crewai.mcp`. It lets you apply a `tool_filter` to give specific agents only the tools they need for their role. Your 'Reporting Agent' gets read-only tools, while your 'Compliance Agent' gets tools to check permissions. It's a straightforward way to build specialized, secure agent teams.

Setup guide

Set up Credly MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Credly tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Credly Analyst",
    goal="Access and analyze Credly data via MCP.",
    backstory="Expert analyst with direct Credly access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Credly transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Credly Analyst",
        goal="Access and analyze Credly data via MCP.",
        backstory="Expert analyst with direct Credly access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Credly transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Use the `MCPServerHTTP` class from `crewai.mcp`. When you initialize it, pass a `tool_filter` list with the exact tool names you want, like `['get_badge_details']`. Then just assign that server instance to your agent.

The `get_badge_details` tool gives you everything about a single issued badge. You'll see the recipient's info, the issue and expiration dates, and the specific evidence or criteria they met to earn it.

Yes. You can assign an agent to periodically run `list_badge_templates` to watch for new or modified designs. From there, it can use `get_template_details` to pull the full design and issuance criteria for review or logging.

That's a perfect task for a sequential crew. One agent can run `list_badge_skills` to get all available skills. A second agent can then take that list, run `list_badge_recipients`, and cross-reference the data to report on which team members have which certifications.

This server only handles your organization's badge, member, and skill data from Credly. All requests run in a zero-trust, ephemeral sandbox on Vinkius. Your connection is encrypted, and we never log or store your Credly data after a request is complete.

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