How to Use the SuperTokens MCP in LangChain

Q: Can I manage user roles for SuperTokens within LangChain?

Yes. You use the assignroletouser tool to grant permissions or listroles to see what's available, all handled by your agent in a structured way.

Q: How do I manage sessions using SuperTokens and LangChain?

You can create a session using createsession or invalidate it with removesession. This ensures that if an agent completes a task, the user's active context is correctly managed.

Build complex user journeys for LangChain agents using SuperTokens.

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 LangChain

Create your Vinkius account to connect SuperTokens to LangChain — 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Managing User Identity in LangChain

The `supertokens-mcp` server lets your agent manage the full lifecycle of a user. You can start by calling `signup_user`, and then, if needed, use `update_user_metadata` to add critical profile data. Later in the chain, the agent can check permissions using `list_user_roles` before deciding whether to execute an action or call `assign_role_to_user`. This makes your multi-step reasoning reliable.

Session and Account Linking for LangChain

Need the agent to handle account changes? The server provides tools like `link_accounts` and `unlink_accounts`, letting you merge or separate identities. It also manages active sessions with `create_session` or revokes access entirely using `remove_session`. This is key for complex workflows where an agent needs to ensure a user's context is clean before running the next step in the pipeline.

Multi-Step User Lookup with MCP Server

The agent can gather all necessary details about a person by chaining multiple calls. First, use `get_user` to get the ID, then call `get_user_metadata` for extra context. Finally, you might need to adjust permissions using `create_or_update_role`. The sequence of these tool calls dictates what happens next in your LangChain flow.

Setup guide

Set up SuperTokens 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 SuperTokens 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({
    "supertokens-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 SuperTokens 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 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 LangChain

The MCP server exposes all core authentication functions directly as callable tools. Your agent decides when and how to call them based on the current state of the chain.

It guarantees that every step in your reasoning pipeline—from signing up a user to checking their roles—is backed by real, verifiable authentication data. This prevents logic gaps in complex chains.

Yes. You use the `assign_role_to_user` tool to grant permissions or `list_roles` to see what's available, all handled by your agent in a structured way.

This server deals with user identities, including primary account details and associated metadata. It also handles session tokens and assigned roles.

You can create a session using `create_session` or invalidate it with `remove_session`. This ensures that if an agent completes a task, the user's active context is correctly managed.

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