WorkOS MCP Server for Pydantic AI 10 tools — connect in under 2 minutes
Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect WorkOS through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
agent = Agent(
model="openai:gpt-4o",
mcp_servers=[server],
system_prompt=(
"You are an assistant with access to WorkOS "
"(10 tools)."
),
)
result = await agent.run(
"What tools are available in WorkOS?"
)
print(result.data)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About WorkOS MCP Server
Connect your WorkOS account to any AI agent and manage your enterprise identity infrastructure through natural conversation.
Pydantic AI validates every WorkOS tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.
What you can do
- Organization Management — Browse and list all enterprise organizations (tenants), create new records, and manage authorized domains
- SSO Monitoring — List and audit active Single Sign-On (SSO) connections (SAML, OIDC) configured for your enterprise customers
- Directory Sync — Monitor active HRIS and SCIM directory instances and retrieve deep details on sync status and provider types
- Roster Management — Retrieve the complete list of users and organizational groups synced from external directories directly from your agent
- Audit Compliance — Stream and retrieve audit log events for any organization to monitor security and compliance activities
- Tenant Insights — Quickly find unique organization, connection, and directory IDs required for enterprise feature configuration
- Connectivity Health — Verify the status and metadata of SSO links and directory connections to ensure uptime
The WorkOS MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect WorkOS to Pydantic AI via MCP
Follow these steps to integrate the WorkOS MCP Server with Pydantic AI.
Install Pydantic AI
Run pip install pydantic-ai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 10 tools from WorkOS with type-safe schemas
Why Use Pydantic AI with the WorkOS MCP Server
Pydantic AI provides unique advantages when paired with WorkOS through the Model Context Protocol.
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your WorkOS integration code
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
Dependency injection system cleanly separates your WorkOS connection logic from agent behavior for testable, maintainable code
WorkOS + Pydantic AI Use Cases
Practical scenarios where Pydantic AI combined with the WorkOS MCP Server delivers measurable value.
Type-safe data pipelines: query WorkOS with guaranteed response schemas, feeding validated data into downstream processing
API orchestration: chain multiple WorkOS tool calls with Pydantic validation at each step to ensure data integrity end-to-end
Production monitoring: build validated alert agents that query WorkOS and output structured, schema-compliant notifications
Testing and QA: use Pydantic AI's dependency injection to mock WorkOS responses and write comprehensive agent tests
WorkOS MCP Tools for Pydantic AI (10)
These 10 tools become available when you connect WorkOS to Pydantic AI via MCP:
create_workos_organization
Provide the name and a list of authorized domains. Creates a new organization record
get_audit_log_events
Returns a stream of events tracked in the organization. Retrieves audit log events for an organization
get_directory_details
g. Okta, Azure AD) of a directory ID. Retrieves metadata for a specific directory instance
get_organization_details
Retrieves details for a specific organization
get_sso_connection_details
Retrieves details for a specific SSO connection
list_directories
Lists all active Directory Sync instances
list_directory_groups
Lists all groups synced from a directory
list_directory_users
Lists all users synced from a directory
list_sso_connections
Lists all active SSO connections
list_workos_organizations
Lists all organizations in the WorkOS account
Example Prompts for WorkOS in Pydantic AI
Ready-to-use prompts you can give your Pydantic AI agent to start working with WorkOS immediately.
"List all organizations in my WorkOS account."
"Check the status of SSO connections for 'Acme Corp'."
"List all users synced from the directory 'dir_01J...'."
Troubleshooting WorkOS MCP Server with Pydantic AI
Common issues when connecting WorkOS to Pydantic AI through the Vinkius, and how to resolve them.
MCPServerHTTP not found
pip install --upgrade pydantic-aiWorkOS + Pydantic AI FAQ
Common questions about integrating WorkOS MCP Server with Pydantic AI.
How does Pydantic AI discover MCP tools?
MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.Does Pydantic AI validate MCP tool responses?
Can I switch LLM providers without changing MCP code?
Connect WorkOS with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect WorkOS to Pydantic AI
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.