How to Use the Clerk MCP in Pydantic AI

Q: Is the legacy MCPServerHTTP class still supported?

No, you should use the unified MCPToolset class instead, as the older transport-specific classes are deprecated. This unified approach simplifies configuration and supports both Streamable HTTP and SSE transports.

Validate your Clerk user data and active sessions at runtime using Pydantic AI type-safe agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Clerk MCP to Pydantic AI

Create your Vinkius account to connect Clerk to Pydantic AI 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 Clerk with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe user profile lookups in Pydantic AI

`get_user_auth_details` fetches a specific user's configuration and instantly validates the payload against strict runtime schemas. If the Clerk API returns unexpected fields or missing data, your Pydantic AI agent fails immediately instead of processing corrupt information. This strict validation ensures that your application logic never operates on invalid user data. You get guaranteed type safety across your entire authentication pipeline.

Track allowlists with strict schema validation

`list_auth_allowlist` retrieves the exact list of emails and domains permitted to register on your platform. Your agent uses this tool to verify if a new signup request matches your system's access rules. Because Pydantic AI enforces strict data models, any deviation in the allowlist structure triggers a validation error. You can trust that your security checks are backed by solid, typed code.

Monitor active sessions with this MCP Server

`list_active_sessions` lists all active user sessions with their associated devices and IP addresses. Your Pydantic AI agent parses this list to identify session anomalies or outdated client connections. Integrating this MCP Server ensures that your security agents operate on verified, structured JSON. It removes the risk of LLM hallucinations when reading session states.

Setup guide

Set up Clerk MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "clerk-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Clerk tools.",
)

result = await agent.run("List recent Clerk transactions")
print(result.output)

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 Pydantic AI

Install the slim package with MCP support, then instantiate `MCPToolset` with your Vinkius HTTP URL. Pass this toolset directly into the `toolsets` argument of your Pydantic AI Agent. The framework will automatically handle tool registration and schema validation.

The framework will raise a validation error at runtime, preventing the agent from executing further actions with bad data. This protects your system from processing malformed user records or corrupted session details.

Yes, Pydantic AI is model-agnostic, meaning you can use this server with Anthropic, Gemini, or local models. The tool schemas are converted into the correct format for whichever model you choose to drive your agent.

No, you should use the unified `MCPToolset` class instead, as the older transport-specific classes are deprecated. This unified approach simplifies configuration and supports both Streamable HTTP and SSE transports.

All data transactions occur over encrypted HTTPS connections directly between your agent and the secure Vinkius sandbox. Your Clerk session IDs, domain lists, and user profiles are processed entirely in-memory and are immediately destroyed once the request completes.

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