Supercharge your AI with MagicBell. Manage multi-channel alerts from chat.

Q: How do I check if an old broadcast was successful using getbroadcast?

You pass the unique UUID to getbroadcast. The tool returns the status, telling you if it was 'processed' and how many recipients across all channels received it.

Q: What is the difference between listbroadcasts and getbroadcast?

listbroadcasts gives you a summary view of everything sent (like an index). getbroadcast requires a specific UUID to fetch the full, detailed status for just that one message.

Q: Can createbroadcast send messages only via SMS?

Yes. When calling createbroadcast, you can define channel-specific overrides and filters. You control exactly which channels (Email, SMS) receive the alert for that specific payload.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

MagicBell manages notifications and broadcasts right from your AI client. Use the `list_broadcasts` tool to see history across Email, SMS, and Push channels.

You can use `get_broadcast` to check a specific message's delivery status or `create_broadcast` to trigger an alert immediately without touching a dashboard.

What your AI can do

Create broadcast

Sends a brand new multi-channel broadcast alert with specified title, content, and filters.

Get broadcast

Fetches the complete status and metadata for one specific broadcast using its unique ID (UUID).

List broadcasts

Retrieves a list of all broadcasts that have been sent in your project, providing an audit trail.

List all historical broadcasts

Run list_broadcasts to get a paginated list of every broadcast sent, showing titles and unique IDs.

Retrieve specific broadcast details

Use get_broadcast with a UUID to pull the full content, status (e.g., 'processed'), and recipient counts for one message.

Send new multi-channel alerts

create_broadcast sends an alert using specified titles, bodies, and filters across email, SMS, or push channels.

Check delivery status per channel

The server reports which specific channels (Email, Web Push) were used for a broadcast and how many recipients received it.

Ask an AI about this

Compatible AI Apps

OAuth 2.0 Compatible

Claude

ChatGPT

Cursor

Gemini

VS Code

JetBrains

Vercel

Zendesk

+ any other MCP app

Included with Plan

Waiting for input…

AI Agent

MagicBell MCP Server: 3 Tools for Broadcast Management

These three tools allow your agent to manage every aspect of broadcast communication—from listing historical records to sending new alerts across multiple channels.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using MagicBell on Vinkius

Create Broadcast

Sends a brand new multi-channel broadcast alert with specified title, content, and filters.

Get Broadcast

Fetches the complete status and metadata for one specific broadcast using its unique...

List Broadcasts

Retrieves a list of all broadcasts that have been sent in your project, providing an...

Connect to your AI in seconds. Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The MagicBell integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "magicbell": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the MagicBell tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"magicbell": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with MagicBell, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,000+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by MagicBell. 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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 3 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Tracking down a single communication failure shouldn't require jumping between three different admin panels.

Today, if the marketing team sends an announcement, you might have to check the email system for history, then log into the SMS portal for delivery counts, and finally look at the web push dashboard just to confirm it all went out. It’s slow, and every panel has different data formats.

With MagicBell MCP Server, your agent runs `list_broadcasts` and gives you one unified view of history across Email, SMS, and Push. You get a single source of truth about who got what message and when.

MagicBell MCP Server: Triggering alerts with `create_broadcast`

Manually sending an emergency alert means someone has to remember the exact API payload, select the correct channel overrides (SMS vs. Email), and hit 'send'—all while under pressure.

Now, you just tell your agent: 'Send a high-priority outage warning via SMS.' The `create_broadcast` tool handles the complex routing and logging automatically. It's done.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

MagicBell manages all your alerts—the whole shebang, across every channel you use. You connect your AI client directly, and it gives you total control over broadcasting messages using natural language commands. This isn't some dashboard you gotta mess with; your agent runs these tools right from your code editor.

You want to know what happened last week? Use the list_broadcasts tool. It pulls up a paginated list of every single broadcast that’s gone out for your project. You get titles and unique IDs, giving you a full audit trail of all your communication efforts. That's how you track everything.

Need to dig into one specific message? Just grab the UUID and run get_broadcast. This tool fetches the complete status and all the metadata for that single broadcast. It tells you if it was 'processed,' what the full content was, and exactly how many people received it across all channels.

You're getting the deep dive here.

When it’s time to send a message—and you gotta send one—you call create_broadcast. This tool handles sending a brand new multi-channel alert instantly. You specify the title, the body text, and any necessary filters, and MagicBell triggers the alerts across email, SMS, or push channels automatically. It doesn't matter if you want it to hit all three; the server manages that routing for ya.

When a broadcast goes out using create_broadcast, the system is smart about reporting back. The server reports which specific channels were actually used—like Email or Web Push—and gives you a count of how many recipients got hit on each one. This means you know exactly what happened with every single message sent.

Think about it: You don't have to jump through hoops in some web portal just to send an alert or check if Uncle Joe actually got that push notification. Your AI client handles the whole cycle. First, you use list_broadcasts to get a quick overview of all previous sends; you see the titles and unique IDs pop up right away.

If you spot a UUID for something you need details on, you hit get_broadcast. That gives you the full picture: the content, the status confirmation, and the exact recipient count. It’s immediate verification. You're checking the metadata so you know it wasn't just sent; you know it was processed.

And when you need to send a message, that's where create_broadcast shines. You feed it the title and body text—the stuff people gotta read—and tell it what filters to use. It then fires off that alert across email, SMS, or push channels simultaneously. The system takes your single command and executes complex multi-channel routing.

You get confirmation on which specific channel was used for each recipient group, and how many folks got the message. It's airtight.

This whole setup means you keep all your communication control right inside your development environment. You don't gotta break flow switching between tools. Your agent calls list_broadcasts to see history; it calls get_broadcast when it needs confirmation on a specific alert ID; and it uses create_broadcast the second an alert is necessary.

It’s seamless, baby.

Built · Hosted · Managed by Vinkius MagicBell MCP Server - Manage Multi-Channel Alerts

Server ID 019e38bb-67cb-7185-96b7-56c70ea23533

Vinkius Inspector

Compliance Grade F

Score 3.6/100

Report View Report ↗

Here's how it actually works

The bottom line is, your AI client uses these tools to talk directly to MagicBell's API, letting you manage complex alerts without writing any code outside of your prompt.

First, subscribe to the MagicBell server and enter your project JWT into your AI client.

Then, tell your agent what you need. For example: 'List all broadcasts from last week.'

The agent executes list_broadcasts (or another tool) and returns the data—the full message history is ready for you to read.

Who is this actually for?

You're the Ops Engineer who gets paged at 3 AM because a system announcement failed. You're the Product Manager who needs to send an emergency feature update but can't find the right person in IT. This server gives you instant, API-level control over your company's communication channels.

Site Reliability Engineer (SRE)

Uses get_broadcast to quickly verify if a critical system alert was actually delivered and processed by all target services.

Product Manager

Runs create_broadcast to send an urgent, company-wide announcement (like a feature update) without needing developer help or logging into the management dashboard.

Customer Support Lead

Uses list_broadcasts to audit communication history and confirm if a specific user group received an important onboarding message last month.

What Changes When You Connect

See the full history of all communications by running list_broadcasts. You get an immediate audit trail without clicking through multiple dashboards or reports.

Check a specific message's delivery status instantly. Use get_broadcast to confirm if 1,240 people actually got the 'Maintenance Notice' across Email and Web Push.

Trigger emergency alerts on the fly. Calling create_broadcast lets you send an urgent announcement immediately when something breaks, no manual deployment required.

Control specific channels for better targeting. When calling create_broadcast, you can set overrides so a message only goes out via SMS, even if email is primary.

Keep communication logs centralized. The server aggregates status and metadata from multiple channels (Email, SMS, Push) into one accessible API endpoint.

See it in action

01 01

A critical system alert needs to go out immediately.

The SRE notices a service degradation. Instead of opening the internal dashboard and manually triggering the announcement flow, they prompt their agent: 'Run create_broadcast for an outage notice.' The tool executes, sending the message across all necessary channels (SMS and Push) instantly.

02 02

Need to confirm if a quarterly update reached everyone.

The Product Manager needs to verify who saw the 'Q3 Feature Rollout' announcement. They prompt their agent: 'Run get_broadcast for UUID 4f1...' The server returns the exact status, showing how many people received it across different channels.

03 03

Auditing a campaign that ran last week.

The Support Lead needs to prove when and what was communicated during an incident. They run list_broadcasts. The agent pulls the full history, allowing them to quickly confirm the 'System Alert' went out exactly at 2:00 PM.

04 04

A small feature requires a targeted announcement.

The team wants to announce a change only to internal users. They use create_broadcast, setting filters that restrict the broadcast payload to 'internal' recipients, ensuring external customers don't see it.

The honest tradeoffs

Assuming all broadcasts are visible.

Anti-pattern

A user tries to check a message they know was sent but doesn't have the UUID. They just ask, 'Show me the alert.'

The Fix

Always start by listing history first. Use list_broadcasts to get recent IDs, then use get_broadcast on the specific ID you need.

Trying to send an ad-hoc message without tracking.

Anti-pattern

A user calls a general messaging tool and sends text that isn't logged or tracked for delivery metrics. They have no way of knowing if it worked.

The Fix

You must use create_broadcast. This tool ensures the message is logged, tracks its multi-channel routing (Email/SMS), and provides a record for future auditing.

Overloading the system with too many calls.

Anti-pattern

Calling get_broadcast repeatedly on IDs that are already known to be processed. This wastes API quota and doesn't provide new information.

The Fix

Before checking status, review the summary list using list_broadcasts. If the list shows the required ID is present, then proceed with get_broadcast.

When It Fits, When It Doesn't

Use this server if you need to treat notifications like a service layer: creation, retrieval, and listing must be auditable. This is for teams that needs guaranteed tracking across multiple channels (Email, SMS, Push).

Don't use it if your goal is simple one-off chat messaging or internal memo passing—use a dedicated communication platform instead. If you only need to read basic logs without status details, other log aggregation tools might suffice.

However, if you are managing core business announcements and need the ability to programmatically verify delivery success (i.e., did it hit 1,240 recipients?), then MagicBell's combination of get_broadcast and list_broadcasts is necessary.

Questions you might have

How do I check if an old broadcast was successful using get_broadcast? +

You pass the unique UUID to get_broadcast. The tool returns the status, telling you if it was 'processed' and how many recipients across all channels received it.

What is the difference between list_broadcasts and get_broadcast? +

list_broadcasts gives you a summary view of everything sent (like an index). get_broadcast requires a specific UUID to fetch the full, detailed status for just that one message.

Can create_broadcast send messages only via SMS? +

Yes. When calling create_broadcast, you can define channel-specific overrides and filters. You control exactly which channels (Email, SMS) receive the alert for that specific payload.

Does MagicBell track multiple broadcast types? +

The server logs all broadcasts passing through it. By using list_broadcasts, you can see a comprehensive history of different campaign types or alerts sent via your project.

What authentication key do I need to provide when running list_broadcasts? +

You must use your MagicBell Project JWT. This token authenticates your agent and grants it permission to view the specific broadcast history for that project. You don't send generic credentials; you send the unique project key.

If a broadcast fails, what details can I get using get_broadcast? +

The metadata includes detailed failure status and an error code. This lets you know if the failure was due to bad content, invalid recipient lists, or a channel-specific issue (like an expired API key for SMS).

Are there rate limits when I use create_broadcast? +

Yes, MagicBell enforces rate limits tied to your subscription tier. If you hit the limit, the server sends a 429 error code, telling your agent exactly how long to wait before retrying the broadcast.

How do I ensure only specific groups receive messages with create_broadcast? +

You specify recipient filters in the payload. You can target users by segment, ID list, or even restrict delivery based on channel type (e.g., email-only). This prevents sending announcements to unintended audiences.

Can I send a notification to specific users or groups? +

Yes! When using the create_broadcast tool, you can provide an array of user IDs or emails in the recipients field to target specific individuals or segments.

How do I check if a broadcast has been successfully processed? +

You can use the get_broadcast tool with the unique broadcast ID. It will return the current processing status and metadata for that specific notification event.

Is it possible to customize the message content for different channels like Email or SMS? +

Absolutely. The create_broadcast tool includes an overrides parameter where you can specify different content or templates for specific channels (email, sms, push).

Connect to your AI in seconds.

Create broadcast

Get broadcast

List broadcasts

MagicBell MCP Server: 3 Tools for Broadcast Management

Make your AI actually useful.

Create Broadcast

Get Broadcast

List Broadcasts

Connect to your AI in seconds. Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Tracking down a single communication failure shouldn't require jumping between three different admin panels.

MagicBell MCP Server: Triggering alerts with `create_broadcast`

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

A critical system alert needs to go out immediately.

Need to confirm if a quarterly update reached everyone.

Auditing a campaign that ran last week.

A small feature requires a targeted announcement.

The honest tradeoffs

Assuming all broadcasts are visible.

Trying to send an ad-hoc message without tracking.

Overloading the system with too many calls.

When It Fits, When It Doesn't

Questions you might have