4,000+ servers built on vurb.ts
Vinkius

Novu MCP Server for Pydantic AIGive Pydantic AI instant access to 39 tools to Bulk Update Subscriber Preferences, Cancel Trigger, Check Topic Subscriber, and more

MCP Inspector GDPR Free for Subscribers

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Novu through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Ask AI about this MCP Server for Pydantic AI

The Novu MCP Server for Pydantic AI is a standout in the Developer Tools category — giving your AI agent 39 tools to work with, ready to go from day one.

Built for AI Agents by Vinkius

Vinkius delivers Streamable HTTP and SSE to any MCP client

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
python
import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Novu "
            "(39 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Novu?"
    )
    print(result.data)

asyncio.run(main())
Novu
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Novu MCP Server

Connect your Novu account to any AI agent and take full control of your notification infrastructure through natural conversation.

Pydantic AI validates every Novu tool response against typed schemas, catching data inconsistencies at build time. Connect 39 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

  • Triggering & Events — Trigger single, bulk, or broadcast notifications across Email, SMS, Push, and Chat using workflow identifiers.
  • Subscriber Management — Create, retrieve, update, and search for subscribers to maintain an up-to-date communication database.
  • Preference Controls — Inspect and update subscriber-specific notification preferences to ensure compliance and user satisfaction.
  • Workflow Cancellation — Cancel active or pending workflows, such as digests or delayed notifications, using transaction IDs.
  • Tenant Context — Manage notifications within specific tenant contexts for multi-tenant applications.

The Novu MCP Server exposes 39 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — credentials fully managed, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

All 39 Novu tools available for Pydantic AI

When Pydantic AI connects to Novu through Vinkius, your AI agent gets direct access to every tool listed below — spanning notification-infrastructure, multi-channel, subscriber-management, and more. Every call runs in a secure, isolated environment with full audit visibility. Beyond a simple connection, you get real-time monitoring of agent activity, enterprise governance, and optimized token usage.

bulk

Bulk update subscriber preferences on Novu

Bulk update subscriber preferences

cancel

Cancel trigger on Novu

Cancel active or pending workflows (e.g., digests, delays)

check

Check topic subscriber on Novu

Check if a subscriber is subscribed to a topic

create

Create environment variable on Novu

Create an environment variable

create

Create integration on Novu

Create a new integration

create

Create layout on Novu

Create a new layout

create

Create subscriber on Novu

Create a new subscriber

create

Create topic on Novu

Create a new topic

create

Create topic subscriptions on Novu

Create subscriptions for a topic

create

Create workflow on Novu

Create a new workflow

delete

Delete integration on Novu

Delete an integration

delete

Delete message on Novu

Delete a message

delete

Delete messages by transaction on Novu

Delete messages by transaction ID

delete

Delete subscriber on Novu

Delete a subscriber

delete

Delete subscriber credentials on Novu

Delete subscriber credentials

delete

Delete topic on Novu

Delete a topic

delete

Delete topic subscriptions on Novu

Delete subscriptions from a topic

get

Get environment variable usage on Novu

Retrieve usage of an environment variable

get

Get subscriber on Novu

Retrieve a subscriber by ID

get

Get subscriber preferences on Novu

Retrieve subscriber preferences

get

Get topic on Novu

Retrieve a topic by key

get

Get topic subscription on Novu

Retrieve a topic subscription

list

List active integrations on Novu

List active integrations

list

List environment variables on Novu

List all environment variables

list

List integrations on Novu

List all integrations

list

List messages on Novu

List messages

list

List topic subscriptions on Novu

List subscriptions for a topic

search

Search subscribers on Novu

Search for subscribers

set

Set primary integration on Novu

Set an integration as primary

trigger

Trigger broadcast on Novu

Send a notification to all existing subscribers

trigger

Trigger bulk event on Novu

Trigger multiple events in a single request

trigger

Trigger event on Novu

Trigger a notification to one or more subscribers

update

Update environment variable on Novu

Update an environment variable

update

Update integration on Novu

Update an integration

update

Update subscriber on Novu

Update an existing subscriber

update

Update subscriber credentials on Novu

Update subscriber credentials

update

Update subscriber preference on Novu

Update a subscriber preference

update

Update topic on Novu

Update a topic

upsert

Upsert subscriber credentials on Novu

Upsert subscriber credentials

Connect Novu to Pydantic AI via MCP

Follow these steps to wire Novu into Pydantic AI. The entire setup takes under two minutes — your credentials stay safe behind Vinkius.

01

Install Pydantic AI

Run pip install pydantic-ai
02

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token
03

Run the agent

Save to agent.py and run: python agent.py
04

Explore tools

The agent discovers 39 tools from Novu with type-safe schemas

Why Use Pydantic AI with the Novu MCP Server

Pydantic AI provides unique advantages when paired with Novu through the Model Context Protocol.

01

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

02

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Novu integration code

03

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

04

Dependency injection system cleanly separates your Novu connection logic from agent behavior for testable, maintainable code

Novu + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Novu MCP Server delivers measurable value.

01

Type-safe data pipelines: query Novu with guaranteed response schemas, feeding validated data into downstream processing

02

API orchestration: chain multiple Novu tool calls with Pydantic validation at each step to ensure data integrity end-to-end

03

Production monitoring: build validated alert agents that query Novu and output structured, schema-compliant notifications

04

Testing and QA: use Pydantic AI's dependency injection to mock Novu responses and write comprehensive agent tests

Example Prompts for Novu in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Novu immediately.

01

"Trigger the 'welcome-onboarding' workflow for subscriber 'user_99' with the payload { "name": "Alice" }."

02

"Search for a subscriber with the email 'support@example.com'."

03

"Cancel the notification trigger with transaction ID 'tx_abc123'."

Troubleshooting Novu MCP Server with Pydantic AI

Common issues when connecting Novu to Pydantic AI through Vinkius, and how to resolve them.

01

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Novu + Pydantic AI FAQ

Common questions about integrating Novu MCP Server with Pydantic AI.

01

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
02

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
03

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Novu MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.

Explore More MCP Servers

View all →