How to Use the Clerk MCP in OpenAI Agents SDK

Q: How do I connect Clerk to the OpenAI Agents SDK?

Install the package and pass the Vinkius endpoint to MCPServerStreamableHttp. Add that to your mcpservers array in the Agent constructor. Set cacheToolsList=True to speed up tool discovery.

Q: Can my agent create new Clerk organizations automatically?

Yes, it calls the createauthorganization tool. You should set up guardrails to require human approval before the agent executes the action.

Q: How do I find specific users in Clerk with OpenAI Agents SDK?

The agent uses getauthuserdetails to pull the profile. It reads the JSON response and formats the details based on your system prompt.

Manage users directly from your OpenAI Agents SDK system with this managed MCP connection.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Clerk MCP to OpenAI Agents SDK

Create your Vinkius account to connect Clerk to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Clerk with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

User Management for OpenAI Agents

Your deployed agents need to know who they are talking to. This MCP Server lets your OpenAI agent pull exact profiles using `get_auth_user_details`. You get the actual identity data injected straight into your prompt context. Need to audit the whole system? The agent can run `list_auth_users` to pull the directory. Everything gets tracked in the OpenAI dashboard, so you always see exactly which agent accessed what user data.

Organization Control

Multi-tenant apps require strict boundaries. You can wire up specialized agents to handle tenant creation by calling `create_auth_organization`. Hand the setup off to an admin agent and let it build the workspace. Listing active tenants is just as easy with `list_auth_organizations`. Built-in guardrails in the SDK ensure your agent never touches organizations outside of its allowed scope.

Invite Workflows

Onboarding new accounts usually means jumping through API hoops. Now your agent can trigger `create_auth_invitation` directly during a conversation. The user asks for a seat, and the system sends the email. Pending invites sit in a queue that your agent can check via `list_auth_invitations`. You set the safety constraints, and the agent handles the follow-ups without you writing custom polling logic.

Setup guide

Set up Clerk MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Clerk tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Clerk tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Clerk tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Clerk Agent",
            instructions="You have access to Clerk tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Clerk. 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 Clerk 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 Clerk MCP in OpenAI Agents SDK

Install the package and pass the Vinkius endpoint to `MCPServerStreamableHttp`. Add that to your `mcp_servers` array in the Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Yes, it calls the `create_auth_organization` tool. You should set up guardrails to require human approval before the agent executes the action.

Every tool execution shows up in your OpenAI tracing dashboard. You see the exact payload sent to the auth endpoints and the response that came back.

The agent uses `get_auth_user_details` to pull the profile. It reads the JSON response and formats the details based on your system prompt.

Vinkius runs the connection in an ephemeral V8 Isolate Sandbox. Your emails, user IDs, and organization names pass through a zero-trust environment that shuts down the moment the request finishes.

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