How to Use the Descope (Auth Platform) MCP in LangChain

Q: Can a LangChain agent handle passwordless email sign-ins with Descope (Auth Platform)?

Yes, the agent calls authmagiclinksignupemail and awaits the user action. The next step in your LangChain graph uses authmagiclinkverify to confirm the token.

Q: Can I manage tenant permissions dynamically within a LangChain run?

Yes, your agent uses mgmtcreatepermission and mgmtcreaterole based on context. This allows real-time access control adjustments during a conversation.

LangChain agents run multi-step authentication and tenant onboarding pipelines using Descope (Auth Platform) tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Descope (Auth Platform) MCP to LangChain

Create your Vinkius account to connect Descope (Auth Platform) to LangChain 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 Descope (Auth Platform) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Descope (Auth Platform) signups with LangChain

LangChain agents use `auth_otp_signup_email` to kick off email-based registrations directly inside your active run. The tool handles sending the code, and your agent waits for the response to trigger the verification step. Once verified via `auth_otp_verify_email`, the chain feeds the output into `mgmt_create_user` to establish the profile. You watch the entire transition inside LangSmith to verify execution order.

Provision tenants inside LangChain reasoning loops

Your LangChain agent evaluates incoming organization requests and runs `mgmt_create_tenant` to spin up isolated spaces. This MCP Server lets the agent determine the tenant structure dynamically before assigning security parameters. The pipeline continues as the agent calls `mgmt_create_role` and `mgmt_create_permission` to lock down the tenant. Every action gets traced in LangSmith so you can audit permissions.

Run passwordless flows in LangChain ReAct loops

Handling complex sign-ins is straightforward when your LangChain agent executes `auth_enchantedlink_signup` to initiate a secure login. The agent pauses, polls the session using `auth_enchantedlink_poll`, and processes the result. If the poll succeeds, the agent triggers `auth_enchantedlink_verify` to validate the user. This multi-server MCP setup keeps your auth logic inside a single conversational run.

Setup guide

Set up Descope (Auth Platform) 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 Descope (Auth Platform) 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({
    "descope-auth-platform-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 Descope (Auth Platform) 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 Descope. 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 Descope (Auth Platform) 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 Descope (Auth Platform) MCP in LangChain

Install langchain-mcp-adapters and langgraph via pip. Initialize MultiServerMCPClient with the Vinkius endpoint, pull the tools, and pass them to your agent constructor.

Yes, the agent calls auth_magiclink_signup_email and awaits the user action. The next step in your LangChain graph uses auth_magiclink_verify to confirm the token.

Use LangSmith tracing to monitor every tool call. You will see the exact inputs for auth_otp_signin_email and the latency of the response.

Yes, your agent uses mgmt_create_permission and mgmt_create_role based on context. This allows real-time access control adjustments during a conversation.

Vinkius processes all requests inside an isolated V8 sandbox, ensuring your session tokens are never stored. The server acts as a direct pass-through to Descope, transmitting data over encrypted channels.

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