How to Use the WorkOS MCP in CrewAI

Q: Can I track directory sync status with WorkOS and CrewAI?

Yes. By using listdirectories, you get all active instances. You can then have a dedicated monitoring agent watch these results, ensuring that no directories fall out of sync without an alarm being raised.

Q: Does WorkOS support listing all groups with CrewAI?

Absolutely. The listdirectorygroups tool lets you pull a complete list of synced groups. Your crew can then assign roles: one agent lists, and another analyzes the group names for naming conventions.

Q: How do I verify organization details using WorkOS and CrewAI?

You'll use getorganizationdetails. The agents can run this check repeatedly within a pipeline. If the data changes between runs, the system flags it immediately for review.

Run autonomous IT operations using WorkOS with CrewAI's multi-agent collaboration framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect WorkOS MCP to CrewAI

Create your Vinkius account to connect WorkOS 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 WorkOS with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Identify Target Users

An agent can use `list_directory_users` to pull all synced users from a directory. A second, specialized agent can then analyze this list, filtering out dormant accounts based on defined criteria. This collaborative approach ensures the final action is highly targeted. It's perfect for building automated compliance checks that need multiple steps of review.

Audit Organizational Activity

One agent retrieves all event streams using `get_audit_log_events`. A moderator agent then watches the session, flagging any events related to unauthorized changes in organizational settings. This shared memory capability keeps track of everything that happens. This structured collaboration allows for deep analysis without requiring a human monitor.

Manage Directory Metadata

To check directory metadata, agents can call `get_directory_details`. The process is role-based: Agent A gets the details; Agent B compares them against the required schema. If they don't match, Agent C takes action by sending an alert. This hierarchical execution models real IT operations perfectly.

Setup guide

Set up WorkOS 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 WorkOS tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent WorkOS 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="WorkOS Analyst",
        goal="Access and analyze WorkOS data via MCP.",
        backstory="Expert analyst with direct WorkOS access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent WorkOS 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 WorkOS. 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 WorkOS 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 WorkOS MCP in CrewAI

CrewAI passes the MCP tool results to specialized agents. You can set up a sequence: Agent 1 uses `list_workos_organizations` (Research), and Agent 2 uses that data to build an action plan (Analyze).

Yes. By using `list_directories`, you get all active instances. You can then have a dedicated monitoring agent watch these results, ensuring that no directories fall out of sync without an alarm being raised.

The server provides structured IT configuration data: organization records, directory metadata, user lists, and SSO connection details. These are the inputs for your autonomous agents to process.

Absolutely. The `list_directory_groups` tool lets you pull a complete list of synced groups. Your crew can then assign roles: one agent lists, and another analyzes the group names for naming conventions.

You'll use `get_organization_details`. The agents can run this check repeatedly within a pipeline. If the data changes between runs, the system flags it immediately for review.

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