Can I target specific users instead of sending to everyone?

Yes! Use the `create_notification` tool and provide a list of `include_player_ids`. This ensures the notification is only delivered to the specific devices you've identified.

How can I check if a scheduled notification was actually sent?

You can use the `get_notification` tool with the Notification ID. It will return real-time delivery metrics, including the number of successful deliveries and current status.

Is it possible to manage multiple OneSignal apps?

Yes. While the core operations use the primary App ID provided in credentials, you can use `list_apps` (requires User Auth Key) to see all your applications and their respective IDs.

OneSignal MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: OneSignal
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

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

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

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 OneSignal "
            "(10 tools)."
        ),
    )

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

asyncio.run(main())

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 OneSignal MCP Server

Connect your OneSignal account to any AI agent and take full control of your customer engagement workflows through natural conversation.

Pydantic AI validates every OneSignal tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the 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

Notifications Management — Send, schedule, and cancel push notifications across mobile and web platforms.
Audience Targeting — Target specific segments or individual player IDs to ensure the right message reaches the right user.
Delivery Analytics — Fetch detailed reports and metrics for any notification to understand your engagement levels.
Device Management — List, inspect, and manage registered devices (players) within your OneSignal applications.
App Overview — List all your OneSignal apps and configurations to maintain a bird's-eye view of your notification infrastructure.

The OneSignal MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect OneSignal to Pydantic AI via MCP

Follow these steps to integrate the OneSignal MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

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

Explore tools

The agent discovers 10 tools from OneSignal with type-safe schemas

Why Use Pydantic AI with the OneSignal MCP Server

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

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

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

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

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

OneSignal + Pydantic AI Use Cases

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

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

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

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

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

OneSignal MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect OneSignal to Pydantic AI via MCP:

cancel_notification

Cancel a scheduled notification

create_notification

Send a OneSignal notification

delete_player

Delete a registered device

get_app

Requires User Auth Key. Get details for a specific OneSignal app

get_notification

Get specific notification status

get_outcomes

Get outcome data for the app

get_player

Get specific player details

list_apps

Requires User Auth Key. List all OneSignal apps

list_notifications

List notifications sent for the app

list_players

List registered devices (players)

Example Prompts for OneSignal in Pydantic AI

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

"Send a push notification to all subscribed users saying 'Flash Sale: 50% off today only!'"

"Check the delivery status of notification 550e8400-e29b-41d4-a716-446655440000."

"List the last 5 registered devices for our app."

Troubleshooting OneSignal MCP Server with Pydantic AI

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

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

OneSignal + Pydantic AI FAQ

Common questions about integrating OneSignal MCP Server with Pydantic AI.

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.

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.

Can I switch LLM providers without changing MCP code?

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