How to Use the MagicBell MCP in CrewAI

Equip your CrewAI teams with MagicBell to coordinate and dispatch system-wide alerts autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MagicBell MCP to CrewAI

Create your Vinkius account to connect MagicBell to CrewAI 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 MagicBell with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Dispatch autonomous team notifications

The `create_broadcast` tool allows your crew of agents to send targeted notifications without human intervention. A monitoring agent can detect a system issue, while a communications agent triggers the broadcast tool to alert the engineering team. This setup turns manual incident response into an autonomous operation. Your agents collaborate in real-time, deciding who needs to know what, and then dispatching the messages instantly.

Monitor sent alerts via this MCP Server

The `list_broadcasts` tool gives your agent crew a full view of all active and past notifications in the project. A supervisor agent can analyze this list to ensure that the team is not sending conflicting or redundant messages. CrewAI agents share memory, meaning the results of this tool are instantly accessible to all members of the crew. This shared context ensures consistent decision-making across your entire automated team.

Investigate specific notification failures

The `get_broadcast` tool retrieves detailed metadata for a specific notification run to help your agents debug delivery issues. When an alert fails, an analyst agent can fetch the broadcast details to inspect the payload and error logs. The agent then uses this information to fix the issue or escalate it to a human developer. This self-healing loop keeps your communication pipeline running smoothly without manual oversight.

Setup guide

Set up MagicBell MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke MagicBell tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="MagicBell Analyst",
    goal="Access and analyze MagicBell data via MCP.",
    backstory="Expert analyst with direct MagicBell access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent MagicBell transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="MagicBell Analyst",
        goal="Access and analyze MagicBell data via MCP.",
        backstory="Expert analyst with direct MagicBell access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent MagicBell transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect MagicBell 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 MagicBell MCP in CrewAI

You can pass your Vinkius server URL directly to the CrewAI agent's config. This gives that specific agent access to `create_broadcast`, `get_broadcast`, and `list_broadcasts`.

Yes. Since CrewAI supports parallel execution, your research agent can look up alert history using `list_broadcasts` while your support agent triggers a new alert using `create_broadcast`.

No. CrewAI natively supports MCP servers. You simply connect the server endpoint, and the framework automatically exposes the tools to your agents as standard Python tools.

You can use CrewAI's hierarchical process model to assign a manager agent that reviews and approves every call to the MCP tool before it actually fires.

All API requests containing user IDs and notification content are encrypted in transit. The Vinkius sandbox ensures that no payload data persists on the host after the tool execution completes.

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