How to Use the Hanko (Passkey Auth) MCP in LangChain

Q: Can Hanko (Passkey Auth) manage credentials for LangChain users?

Yes, use passkeylistcredentials and passkeydeletecredential as available tools for your agent. The agent can then audit and remove compromised keys on behalf of the user.

Q: Does LangChain support Hanko (Passkey Auth) flow execution?

It does. You can call flowexecute directly within your chain to handle complex authentication sequences that require multi-step interaction.

Build secure, passwordless identity chains in LangChain with Hanko (Passkey Auth) and managed MCP server tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hanko (Passkey Auth) MCP to LangChain

Create your Vinkius account to connect Hanko (Passkey Auth) 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 Hanko (Passkey Auth) with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chainable passkey authentication logic

Integrate credential flows directly into your LangChain agent pipelines. Use `passkey_registration_init` to start the challenge and pipe the output to your frontend, ensuring the agent maintains state across every step of the registration process. Your agent controls the entire lifecycle by chaining `passkey_registration_finalize` immediately after user interaction. This keeps your auth logic as a distinct, observable step within your LangSmith traces.

Automated session verification in LangChain

Offload your security checks to the Hanko (Passkey Auth) MCP server during agent execution. By calling `public_validate_session` as a tool, you ensure that every action performed by your agent is backed by a verified identity token. This prevents unauthorized tool access by validating tokens before the agent triggers downstream operations. Your chains remain secure without manual session overhead.

Admin-level identity management

Manage user accounts through your agent by invoking the admin suite of tools. Use `admin_list_users` to query your database and `admin_get_user` to inspect specific identity profiles directly from your LangChain flow. This lets your agents handle help-desk tasks or account cleanup automatically. You define the logic, and the agent executes the precise admin call needed to resolve the ticket.

Setup guide

Set up Hanko (Passkey Auth) 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 Hanko (Passkey Auth) 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({
    "hanko-passkey-auth-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 Hanko (Passkey Auth) 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 Hanko. 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 Hanko (Passkey Auth) 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 Hanko (Passkey Auth) MCP in LangChain

Connect the MCP server to your agent and wrap sensitive tools with `public_validate_session`. You'll force the agent to check the user's token before it runs any critical operations.

Yes, use `passkey_list_credentials` and `passkey_delete_credential` as available tools for your agent. The agent can then audit and remove compromised keys on behalf of the user.

It does. You can call `flow_execute` directly within your chain to handle complex authentication sequences that require multi-step interaction.

The server handles all sensitive biometric data and private keys on the client side. Your application only interacts with public JWKS keys for validation.

Yes, the transport is ephemeral and secured via the Vinkius sandbox. No session data is stored on our servers after the connection terminates.

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