How to Use the PushEngage MCP in CrewAI

Q: How do I assign PushEngage tools from an MCP Server to a specific CrewAI agent?

Pass the MCP Server URL in the agent's mcps parameter. You can restrict that agent to only listpushengagesubscribers while keeping broadcast tools locked.

Q: How does CrewAI monitor active PushEngage triggers?

An agent runs listpushengagetriggers to fetch active automated flows. CrewAI then processes this data to decide if new notification rules need to be built.

Q: How do I set up CrewAI with this server over HTTP?

Import MCPServerHTTP from crewai.mcp and point it to your Vinkius endpoint. This connects your Python crew to the push notification tools over a secure SSE transport.

Deploy a crew of autonomous agents to audit, segment, and run PushEngage push campaigns using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PushEngage MCP to CrewAI

Create your Vinkius account to connect PushEngage to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PushEngage with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-agent PushEngage campaigns with CrewAI

Let a team of specialized CrewAI agents manage your PushEngage marketing. One CrewAI agent can analyze historical alerts using `list_pushengage_notifications`, while another drafts new copy and runs `send_pushengage_broadcast` when performance targets are met. This collaborative CrewAI setup removes the need for manual PushEngage scheduling. The MCP Server acts as the bridge, giving each agent in the crew access to the exact PushEngage tools they need to execute their specific roles.

Autonomous subscriber list grooming

Keep your PushEngage audience lists clean without manual data exports using CrewAI. A researcher agent calls `list_pushengage_subscribers` and `list_pushengage_segments` using the MCP Server to find inactive records. The CrewAI team then flags these PushEngage segments for review. By automating this cleanup, you ensure your active PushEngage notification campaigns target high-intent users instead of dead browser profiles.

Continuous automation auditing

Monitor your live PushEngage campaigns around the clock using CrewAI. An auditor agent continuously runs `list_pushengage_triggers` and `check_pushengage_status` to ensure your automated funnels are active. If a PushEngage trigger stops firing, the agent alerts the CrewAI team to pause active broadcasts. This prevents disjointed user experiences when backend PushEngage systems go out of sync.

Setup guide

Set up PushEngage 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 PushEngage tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent PushEngage 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="PushEngage Analyst",
        goal="Access and analyze PushEngage data via MCP.",
        backstory="Expert analyst with direct PushEngage access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent PushEngage 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 PushEngage. 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 PushEngage 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 PushEngage MCP in CrewAI

Pass the MCP Server URL in the agent's `mcps` parameter. You can restrict that agent to only `list_pushengage_subscribers` while keeping broadcast tools locked.

Yes. A copywriter agent can write the message, and a coordinator agent can execute `send_pushengage_broadcast` to push the notification live once approved.

An agent runs `list_pushengage_triggers` to fetch active automated flows. CrewAI then processes this data to decide if new notification rules need to be built.

Import `MCPServerHTTP` from `crewai.mcp` and point it to your Vinkius endpoint. This connects your Python crew to the push notification tools over a secure SSE transport.

No. All communication with the MCP Server goes through Vinkius's ephemeral sandboxed environment. Your subscriber metrics and credentials are never exposed or stored by the Python CrewAI runtime.

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