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

Q: Can a LangChain agent manage organizations using this MCP Server?

Yes. The agent uses tools like createorganization and listorganizationusers to build, query, or modify tenant structures dynamically during a run.

Q: How does LangChain handle errors when calling Logto (Auth Platform) MCP tools?

The framework catches exceptions from tools like verifyuserpassword or deleteuser and passes them back to the LLM. The agent can then decide to try a different tool or ask the user for clarification.

Q: Do I need to write custom code to parse the user list in LangChain?

No. This server returns structured JSON from listusers, which LangChain feeds directly into your agent's context window.

Get your LangChain agents managing user profiles, API resources, and organizations in Logto without writing boilerplates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Logto (Auth Platform) MCP to LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Multi-Step Tenant Provisioning

Build LangChain graphs that handle complex onboarding sequences with this MCP Server. Your agent can run `create_organization` and immediately feed the resulting ID into `create_role` or assign users. This turns manual multi-step tenant setups into single-run executions. Because LangChain traces every step, you see exactly how the agent handles these steps. If `create_resource` fails or returns an unexpected schema, your agent can catch the error and retry with different parameters.

Secure MFA and Profile Updates in Chains

Run secure user-facing workflows through LangChain's ReAct loop. Your agent checks existing configurations with `list_mfa_verifications` before prompting a user to trigger `bind_mfa_verification` or `send_verification_code`. This MCP Server exposes raw tools directly to the chain. The agent decides when to update profiles using `update_my_account_profile` based on user conversation history, maintaining a tight loop of verification and update steps.

Track Logto MCP Server Actions with LangSmith

Monitor every single auth query your LangChain agent makes. Every call to `list_users` or `verify_user_password` gets logged with precise latency and token metrics. You don't have to guess why a user lookup failed. The LangSmith integration tracks the inputs and outputs of `get_user` so you can debug permissions or rate limits in real time.

Setup guide

Set up Logto (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 Logto (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({
    "logto-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 Logto (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 Logto. 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 Logto (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 Logto (Auth Platform) MCP in LangChain

You configure your API token in the Vinkius panel. The LangChain client connects to the hosted endpoint using MultiServerMCPClient, which handles authorization behind the scenes so your local code stays clean.

Yes. The agent uses tools like `create_organization` and `list_organization_users` to build, query, or modify tenant structures dynamically during a run.

The framework catches exceptions from tools like `verify_user_password` or `delete_user` and passes them back to the LLM. The agent can then decide to try a different tool or ask the user for clarification.

No. This server returns structured JSON from `list_users`, which LangChain feeds directly into your agent's context window.

Your user profiles, including emails, passwords, and MFA states touched by `update_my_account_password`, stay encrypted. Vinkius runs the server in an isolated sandbox, meaning raw identity data never lingers on external servers.

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