How to Use the Authkey MCP in LangChain

Q: Does the Authkey toolset support LangSmith tracing?

Yes, every call to getsmsstatus or sendotp made by your LangChain agent through this MCP connection is fully traced in LangSmith, showing you exact payloads and execution times.

Q: Can I fetch templates configured in my dashboard?

Yes, your agent can call listtemplates to fetch your pre-approved message layouts. This ensures your automated messages always match your brand and pass carrier compliance checks.

Run multi-step communication chains in LangChain using Authkey to send texts, emails, and verify OTPs dynamically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authkey MCP to LangChain

Create your Vinkius account to connect Authkey 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 Authkey with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run multi-step verification chains with LangChain

Build LangChain agents that don't just send alerts but follow up on them using `send_otp`. Your agent can run the tool to deliver a verification code, then pause and use `verify_otp` to confirm the user got it. If the OTP fails, the chain can automatically fall back to `send_voice` to read the code over a phone call. Every single step in this workflow runs through the LangSmith dashboard. You get to trace exactly how much latency each Authkey API call adds to your chain, ensuring your user onboarding stays fast and reliable.

Smart balance tracking inside your agent loops

Stop letting your messaging campaigns die because of an empty account by using `check_balance` inside your agent loops. With this MCP Server, your agent checks your remaining credits before triggering a high-volume notification run. If the funds run low, the agent can pause the queue or ping your team channel with the exact balance. It keeps your messaging pipeline running without manual oversight.

Bulk message dispatch with full delivery tracing

Triggering massive notification blasts is easy when your agent uses `send_bulk_sms`. You don't have to write custom loops or handle batching logic yourself; just pass the list of recipients directly to the tool. After dispatching, your agent can poll `list_sms_history` or check specific delivery logs using `get_sms_status`. You get real-time feedback on which messages landed and which bounced.

Setup guide

Set up Authkey 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 Authkey 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({
    "authkey-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 Authkey 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 Authkey. 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 Authkey 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 Authkey MCP in LangChain

You pass your Vinkius endpoint token to the MultiServerMCPClient during initialization. The MCP Server handles the actual Authkey API keys on our secure backend, so your LangChain code never exposes raw credentials.

Yes, you can build retry logic directly into your LangGraph or LangChain chains. If you connect this MCP integration, your agent can catch errors from `send_sms` and immediately try `send_email` as a backup.

Yes, every call to `get_sms_status` or `send_otp` made by your LangChain agent through this MCP connection is fully traced in LangSmith, showing you exact payloads and execution times.

Yes, your agent can call `list_templates` to fetch your pre-approved message layouts. This ensures your automated messages always match your brand and pass carrier compliance checks.

All phone numbers, OTP codes, and message bodies processed by `send_sms` pass through a zero-trust, ephemeral V8 isolate. We do not write your message history to any persistent storage; it goes straight to Authkey and vanishes from our servers immediately.

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