How to Use the iZooto MCP in LangChain

Q: How do I connect the iZooto MCP Server to LangChain?

Install langchain-mcp-adapters and langgraph via pip. Initialize the MultiServerMCPClient with the Vinkius HTTP endpoint, call gettools(), and pass those tools directly to your agent constructor.

Q: Can LangChain automate personalized push notifications with iZooto?

Yes, your agent can read user attributes, call createsegment to group them, and then execute sendsegmentpush. This lets you run highly targeted re-engagement campaigns based on real-time behavior.

Q: What happens if the iZooto API goes down?

Your agent can use checkizootostatus at the start of a chain to confirm connectivity. If the API is unresponsive, the chain halts safely before attempting to send notifications.

Run multi-step web push campaigns through LangChain using live subscriber data and automated triggers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iZooto MCP to LangChain

Create your Vinkius account to connect iZooto 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 iZooto with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Target specific audiences dynamically

The `create_segment` tool builds custom user groups based on real-time browser behaviors. Your LangChain agent evaluates subscriber activity, builds the segment, and then checks the audience size with `get_subscriber_count` before committing to a campaign. This chain prevents you from blasting your entire list with irrelevant notifications. Instead of running manual imports, you pass the resulting segment ID directly to `send_segment_push`. LangSmith tracks every step of this tool chain, showing you the exact inputs and latency of your audience selection process in real time.

Auto-respond to performance drops

The `get_stats` tool pulls click rates and delivery metrics for your active campaigns. When configured inside a LangChain ReAct loop, your agent monitors these metrics and automatically branches to a different strategy if click-through rates fall below your baseline. If a campaign underperforms, the agent calls `list_notifications` to analyze previous copy patterns. It then drafts a fresh message and fires it using `send_push` to test a new angle without human intervention.

Connect iZooto to your LangChain stack

The `check_izooto_status` tool verifies your connection to the web push API before executing any automated workflow. This MCP server acts as a direct bridge between your LangChain chains and your subscriber database, removing the need for custom API integration code. By exposing tools like `list_segments` and `get_notification` to your agent, you can build complex loops that query, verify, and dispatch updates. The agent runs these actions inside a secure sandbox, keeping your API credentials isolated from the execution environment.

Setup guide

Set up iZooto 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 iZooto 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({
    "izooto-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 iZooto 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 iZooto. 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 iZooto 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 iZooto MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Initialize the MultiServerMCPClient with the Vinkius HTTP endpoint, call `get_tools()`, and pass those tools directly to your agent constructor.

Yes, your agent can read user attributes, call `create_segment` to group them, and then execute `send_segment_push`. This lets you run highly targeted re-engagement campaigns based on real-time behavior.

You get complete visibility through LangSmith tracing. Every time your agent calls `get_stats` or `send_push`, LangSmith logs the exact latency, token usage, and payload details.

Your agent can use `check_izooto_status` at the start of a chain to confirm connectivity. If the API is unresponsive, the chain halts safely before attempting to send notifications.

Vinkius hosts the MCP server in a zero-trust V8 sandbox, meaning subscriber tokens and notification data never leak to the LLM provider. Only the specific payloads needed for tools like `send_push` are transmitted 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