4,000+ servers built on vurb.ts
Vinkius
MagicBell

MagicBell MCP Server with 3 Tools for Claude, Cursor, and AI Agents

MCP Inspector GDPR Free for Subscribers

Manage notifications and broadcasts via MagicBell — list, retrieve, and trigger multi-channel alerts directly from your AI agent. Vinkius routes your AI agents directly to MagicBell through a governed connection. 3 tools ready to use with Claude, ChatGPT, Cursor, or any AI agent — no hosting, no setup, connect in 30 seconds.

Built for AI Agents by Vinkius

Compatible with every major AI agent and IDE

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
AI AgentVinkius
High Security·Kill Switch·Plug and Play
MagicBell
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

What is the MagicBell MCP Server?

The MagicBell MCP Server routes AI agents like Claude, ChatGPT, and Cursor directly to MagicBell via 3 tools. Manage notifications and broadcasts via MagicBell — list, retrieve, and trigger multi-channel alerts directly from your AI agent. Powered by Vinkius — your credentials stay on your side of the connection, every request is auditable. Connect in under 2 minutes.

Built-in capabilities (3)

create_broadcastget_broadcastlist_broadcasts

Tools for your AI Agents to operate MagicBell

Ask your AI agent "List all recent broadcasts in my MagicBell project." and get the answer without opening a single dashboard. With 3 tools connected to real MagicBell data, your agents reason over live information, cross-reference it with other MCP servers, and deliver insights you would spend hours assembling manually.

Works with Claude, ChatGPT, Cursor, and any MCP-compatible client. Powered by Vinkius — your credentials never touch the AI model, every request is auditable. Connect in under two minutes.

Why teams choose Vinkius

One subscription gives you the infrastructure to connect your AI agents to thousands of MCP servers — and deploy your own to the Vinkius Edge. Your credentials stay yours. Your data flows directly between your agent and the API. DLP blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade routing and governance, zero maintenance.

Build your own MCP Server with our secure development framework →

The MagicBell App Connector works with every AI agent you already use

…and any MCP-compatible client

CursorClaudeOpenAIVS CodeCopilotGoogleLovableMistralAWSCursorClaudeOpenAIVS CodeCopilotGoogleLovableMistralAWS

Use all 3 MagicBell tools with your AI agents right now

Vinkius routes your AI agents to MagicBell through a governed proxy. Beyond a simple connection, you get full visibility into every action your agents perform, with enterprise-grade security and up to 60% savings on AI costs.

Explore Tools Hub
create

Create broadcast on MagicBell

Create a new broadcast

get

Get broadcast on MagicBell

Fetch a specific broadcast

list

List broadcasts on MagicBell

List all broadcasts in the project

What the MagicBell MCP Server unlocks

Connect your MagicBell project to any AI agent to orchestrate multi-channel notification workflows. Trigger broadcasts, check delivery status, and manage communication logs through natural conversation.

What you can do

  • Broadcast Management — List all active and past broadcasts sent through your project to track communication history.
  • Detailed Inspection — Fetch specific broadcast metadata, content, and processing status using unique UUIDs.
  • Trigger Notifications — Create and send new broadcasts with custom titles, body content, and specific recipient filters.
  • Multi-channel Control — Handle channel-specific overrides for email, SMS, and push notifications to ensure the right message reaches the right place.

How it works

1. Subscribe to this server
2. Enter your MagicBell Project JWT
3. Start sending and monitoring notifications from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Product Managers — trigger system-wide announcements or feature updates without touching the technical dashboard.
  • Support & Ops Teams — quickly verify if a specific broadcast was successfully processed and delivered to users.
  • Developers — test notification payloads, categories, and overrides directly from your code editor during development.

Frequently asked questions about the MagicBell MCP Server

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).

Vinkius AI Gateway

We built the connector to MagicBell. Now put your agents to work. Fully governed.

Vinkius is the AI Gateway with managed hosting. Stop building connectors. Every connection runs inside eight layers of security.

How it works
Infrastructure

Hosted, sandboxed, and live on AWS. You don't provision anything. You don't maintain anything. You connect.

Visibility

Every tool call, every token, every response. Logged and auditable. Data flows direct from MagicBell to your agent. Nothing is stored on our side. Ever.

Control

Eight governance layers on every request. Sensitive data redacted before it reaches the model. Kill switch if anything goes sideways. Always on.