How to Use the Aimtell MCP in CrewAI

Deploy specialized CrewAI agents to autonomously manage your Aimtell push campaigns via this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aimtell MCP to CrewAI

Create your Vinkius account to connect Aimtell 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 Aimtell with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build autonomous marketing crews

Running push notification strategy usually requires an analyst pulling numbers and a marketer writing copy. You can replace that manual loop by assigning those exact roles to different agents. They talk to each other, analyze the data, and execute changes without waiting for you. Your analyst agent runs `get_campaign_performance` to find underperforming broadcasts. It passes those insights to a copywriter agent, which drafts new alerts. Finally, an execution agent uses `send_one_off_notification` to push the revised messaging live.

Monitor sites via MCP Server agents

Managing multiple websites means someone has to constantly check audience growth across different properties. A dedicated monitoring crew can run on a schedule to audit your entire portfolio. They compile the numbers and drop a formatted report into your Slack channel every morning. The lead agent executes `list_sites` to grab your active properties. It delegates tasks to worker agents that run `list_subscribers` for each specific domain. This parallel execution gathers a massive amount of data quickly, letting the crew spot audience trends across your entire network.

Maintain strict tool boundaries

You probably do not want your research agents accidentally firing off push alerts to a million people. CrewAI lets you restrict exactly what each member of your team can actually do. You give read access to the analysts and write access only to the executors. Instead of passing the raw URL, you use `MCPServerHTTP` combined with `tool_filter`. The analyst gets restricted access to `list_campaigns` and `list_segments`. Only the final approval agent is allowed to touch anything that actually modifies subscriber data or triggers a broadcast.

Setup guide

Set up Aimtell 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 Aimtell tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The easiest method is passing your Vinkius endpoint URL directly into the `mcps` array in your Agent definition. For more granular control, import `MCPServerHTTP` from `crewai.mcp` and configure specific tool filters for each agent.

Yes. If you expose the notification tools to an action agent, it will fire alerts based on the conditions you define. You can set up a hierarchical crew where a manager agent must approve the action before the execution agent sends it.

Writing custom API wrappers for multi-agent setups gets messy fast. This standard protocol gives your crew immediate, structured access to ten different endpoints. They understand the schema natively and know exactly how to call each function.

It works perfectly. Agent A can pull subscriber metrics, pass the exact output to Agent B for analysis, and Agent C can tag the users based on that analysis. The shared memory keeps the context intact across the entire pipeline.

Your agents process raw browser metadata and custom engagement attributes. Vinkius secures this by requiring a single endpoint token and running the execution in an isolated, ephemeral container. The infrastructure leaves zero footprint after the agents finish their tasks.

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