How to Use the SuperTokens MCP in Pydantic AI

Q: How do I manage user roles with SuperTokens using Pydantic AI?

First, you call listroles to see what's available. Then, use createorupdaterole if needed. Finally, your agent executes the change using assignroletouser.

Q: Can I manage multiple tenants with SuperTokens using Pydantic AI?

Yes. You define boundaries by calling createorupdatetenant and then validate the scope using gettenant. This keeps your agent's data actions contained to the right business unit.

Q: Does SuperTokens support session management for Pydantic AI?

Yes. You can start a new login with signinuser and maintain it via refreshsession. This gives your agent predictable, typed access to the user's current context.

Q: What if I need to link accounts in SuperTokens using Pydantic AI?

You use the linkaccounts tool. It allows your agent to merge multiple distinct identifiers into one coherent user profile, making data retrieval much cleaner.

Guaranteed data integrity for production agents using Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SuperTokens MCP to Pydantic AI

Create your Vinkius account to connect SuperTokens to Pydantic AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SuperTokens with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Secure Login and Signup Flow

The primary entry points are `signup_user` and `signin_user`. Your agent uses these tools to establish a user's identity. These functions guarantee the necessary authentication tokens for downstream tasks. After successful login, you can maintain continuous access by calling `refresh_session` or immediately revoking it with `remove_session`.

Manage User Profiles and Metadata

Getting user details is simple using `get_user`. For granular data points, call `get_user_metadata` to retrieve specific attributes. You can then modify this non-critical info with `update_user_metadata`. Need to clean up old data? Use `delete_user_metadata` to explicitly remove fields your agent no longer needs.

Control Account Linking and Roles

You manage complex relationships using `link_accounts` or sever ties with `unlink_accounts`. For permissions, you use `list_user_roles` to check current access. You can assign new rights via `assign_role_to_user`. Don't forget the top-level control: define roles using `create_or_update_role`.

Setup guide

Set up SuperTokens 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": {
        "supertokens-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent SuperTokens 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 SuperTokens. 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 SuperTokens 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 SuperTokens MCP in Pydantic AI

First, you call `list_roles` to see what's available. Then, use `create_or_update_role` if needed. Finally, your agent executes the change using `assign_role_to_user`.

The server handles structured user data: IDs, roles, accounts, and session tokens. Since your agent validates every output with Pydantic, you get high confidence in the returned structure.

Yes. You define boundaries by calling `create_or_update_tenant` and then validate the scope using `get_tenant`. This keeps your agent's data actions contained to the right business unit.

Yes. You can start a new login with `signin_user` and maintain it via `refresh_session`. This gives your agent predictable, typed access to the user's current context.

You use the `link_accounts` tool. It allows your agent to merge multiple distinct identifiers into one coherent user profile, making data retrieval much cleaner.

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