How to Use the WorkOS MCP in LangChain

Q: How does WorkOS data flow with LangChain?

The agent calls tools like listdirectoryusers and receives the raw JSON list. This output then becomes a variable that can be passed directly into the prompt or as input for another tool call in your chain.

Q: Can I use WorkOS with LangChain to audit changes?

Absolutely. You'll run getauditlogevents and feed that event stream directly into your agent. The agent can then decide if a sequence of actions triggered an alert or requires human review.

Build multi-step reasoning agents that manage WorkOS identity and directory sync via LangChain.

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 LangChain

Create your Vinkius account to connect WorkOS 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 WorkOS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Organization Setup

The agent first calls `list_workos_organizations` to see what's already running. Then, it uses `create_workos_organization` when a new client needs setup. This sequence allows the ReAct agent to build an entire operational pipeline: check existence -> create if missing -> proceed with next steps.

Sync and Audit Directory Data

You can gather all necessary account data in one go. The agent runs `list_directory_users` and then uses `get_directory_details` to check the metadata on that synced instance. It’s perfect for debugging or pre-flight checks, letting your chain verify which directory instances are active before writing code.

Monitor SSO Connections

When an agent needs visibility into security posture, it calls `list_sso_connections` to get a roster of all linked services. It can then drill down with `get_sso_connection_details` for specific credentials. This mechanism lets the chain validate if a service is correctly configured before allowing other actions.

Setup guide

Set up WorkOS 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 WorkOS 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({
    "workos-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 WorkOS 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 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 LangChain

The agent calls tools like `list_directory_users` and receives the raw JSON list. This output then becomes a variable that can be passed directly into the prompt or as input for another tool call in your chain.

Absolutely. You'll run `get_audit_log_events` and feed that event stream directly into your agent. The agent can then decide if a sequence of actions triggered an alert or requires human review.

You're managing enterprise-grade identity services. This includes creating new organizations, viewing directory metadata (like Okta/Azure AD), and listing all active SSO connections.

Yes. Because the output of one tool call becomes the input for the next, you can build multi-step logic: check org existence -> get user count -> report findings.

It touches directory metadata, organization records, and SSO connection details. The agent handles these structured identity documents.

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