How to Use the Novu MCP in LangChain

Q: Can I update subscriber options dynamically inside a LangChain sequence?

Yes, you use updatesubscriberpreference as a tool node inside your graph. The output of previous database steps feeds directly into this tool to modify user settings in real-time.

Q: Can this server handle transactional message deletions?

Yes, the server exposes the deletemessagesbytransaction tool for this exact purpose. Your agent calls it with the transaction ID to purge specific outbound alerts instantly.

Q: How is subscriber credential data secured in Novu when using LangChain?

The upsertsubscribercredentials tool processes sensitive access keys inside an ephemeral V8 sandbox. Vinkius isolates this MCP runtime, meaning your API tokens and subscriber credentials never persist on disk or leak into other runtimes.

Trigger multi-channel notifications and manage subscriber preferences directly inside your LangChain reasoning loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Novu MCP to LangChain

Create your Vinkius account to connect Novu 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 Novu with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build context-aware notification chains in LangChain

The `trigger_event` tool initiates multi-channel alerts by passing execution data from preceding chain nodes directly to Novu. Your LangChain agent evaluates user behavior, pulls context from prior steps, and decides when to fire off transactional messages. If a user changes their settings mid-session, the `bulk_update_subscriber_preferences` tool updates their options instantly. You get full visibility over these multi-step runs via LangSmith, which tracks every payload sent through this MCP server without adding system overhead.

Automate subscriber lifecycle updates

The `create_subscriber` tool registers new users in your notification directory during active chain runs. Instead of writing custom API integration glue, you let your ReAct agent handle user registration as a direct response to database changes. When users opt out or delete accounts, the agent executes `delete_subscriber` to keep your lists clean. This approach ensures your backend database and Novu directory stay mirrored without manual cron jobs.

Manage active layout and workflow templates

The `create_workflow` tool builds new notification templates directly from your agent's execution path. This MCP server lets your LangChain pipeline inspect the active setup and generate layouts dynamically based on your app's state. For immediate template adjustments, `create_layout` formats email structures on the fly. This setup reduces the manual work of logging into a dashboard just to update a basic header.

Setup guide

Set up Novu 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 Novu 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({
    "novu-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 Novu 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 Novu. 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 Novu 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 Novu MCP in LangChain

The agent catches API exceptions directly within the run loop when `trigger_event` fails. This MCP integration lets you configure fallback chains to log the error or retry the call using LangSmith tracing.

Yes, you use `update_subscriber_preference` as a tool node inside your graph. The output of previous database steps feeds directly into this tool to modify user settings in real-time.

The framework uses standard rate-limiting wrappers around the MCP tools. If you execute `trigger_broadcast`, the agent schedules the call to respect Novu API thresholds automatically.

Yes, the server exposes the `delete_messages_by_transaction` tool for this exact purpose. Your agent calls it with the transaction ID to purge specific outbound alerts instantly.

The `upsert_subscriber_credentials` tool processes sensitive access keys inside an ephemeral V8 sandbox. Vinkius isolates this MCP runtime, meaning your API tokens and subscriber credentials never persist on disk or leak into other runtimes.

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