How to Use the Novu MCP in Pydantic AI

Q: How does Pydantic AI handle schema mismatches when calling Novu tools?

If the model generates a payload for triggerevent that violates your schema, Pydantic AI throws a validation error. This stops the execution before an invalid API call is made to the MCP Server.

Q: Can I use Pydantic AI to safely update Novu subscriber preferences?

Yes, you can use the updatesubscriberpreference tool within your agent setup. Pydantic AI validates the preference payload structure, ensuring channel settings are correct before updating the profile.

Q: Does Pydantic AI support bulk subscriber updates via Novu?

Yes, the agent can call bulkupdatesubscriberpreferences to update multiple profiles at once. The framework validates the list of preference objects to prevent malformed data from corrupting user records.

Q: How do I connect this MCP Server to my Pydantic AI agent?

You initialize the MCPToolset with the Vinkius HTTP endpoint and pass it to the agent constructor. This exposes all 39 notification tools to your model with automatic schema generation.

Q: What happens to the custom template variables sent in my Novu notification payloads?

All custom template variables processed by triggerevent flow directly through memory inside an isolated V8 sandbox. Vinkius does not store, log, or inspect the contents of your notification payloads, keeping your customer data private.

Build type-safe notification workflows with Pydantic AI to enforce strict schema validation on your Novu API calls.

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 Pydantic AI

Create your Vinkius account to connect Novu to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe Novu event triggers with Pydantic AI

Never worry about sending a broken payload to your Novu gateway again. Pydantic AI validates every single argument passed to `trigger_event` and `trigger_bulk_event` against strict Python types at runtime before the request ever leaves your server. If your model attempts to pass an invalid email format or a missing subscriber ID to Novu, the framework raises a validation error immediately. This prevents silent failures in your production notification pipelines and keeps your delivery logs clean.

Strict subscriber lifecycle management

Manage your Novu user profiles with absolute runtime guarantees. When your Pydantic AI agent calls `create_subscriber` or `update_subscriber`, the framework ensures the subscriber payload perfectly matches your internal database models. The agent can safely fetch user profiles using `get_subscriber` and update their channels with `update_subscriber_preference` without risk of field corruption. This keeps your Novu MCP integration reliable and free of data type errors.

Validated topic and subscription routing

Organize Novu subscriber segments using strictly validated topic tools. This MCP Server lets your Pydantic AI agent run `create_topic` and `create_topic_subscriptions` while enforcing validation rules on topic keys and subscriber lists. This prevents issues where invalid topic formats block your Novu message delivery. The agent validates the output of `list_topic_subscriptions` before routing critical updates, ensuring your transactional messages always land in the right inbox.

Setup guide

Set up Novu MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "novu-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Novu tools.",
)

result = await agent.run("List recent Novu transactions")
print(result.output)

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 Pydantic AI

If the model generates a payload for `trigger_event` that violates your schema, Pydantic AI throws a validation error. This stops the execution before an invalid API call is made to the MCP Server.

Yes, you can use the `update_subscriber_preference` tool within your agent setup. Pydantic AI validates the preference payload structure, ensuring channel settings are correct before updating the profile.

Yes, the agent can call `bulk_update_subscriber_preferences` to update multiple profiles at once. The framework validates the list of preference objects to prevent malformed data from corrupting user records.

You initialize the `MCPToolset` with the Vinkius HTTP endpoint and pass it to the agent constructor. This exposes all 39 notification tools to your model with automatic schema generation.

All custom template variables processed by `trigger_event` flow directly through memory inside an isolated V8 sandbox. Vinkius does not store, log, or inspect the contents of your notification payloads, keeping your customer data private.

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