How to Use the Adikteev MCP in CrewAI

Q: How do I install Adikteev in CrewAI?

Run pip install crewai "crewaitools". For a basic setup, just drop your Vinkius URL into the mcps array on your Agent definition.

Q: How do I restrict which Adikteev tools a CrewAI agent can use?

Import MCPServerHTTP from crewai.mcp and use the toolfilter argument. You can give your analyst agent access to reporting tools while restricting segment creation to your manager agent.

Deploy a team of autonomous CrewAI agents to manage your Adikteev retargeting campaigns and analyze churn.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to CrewAI

Create your Vinkius account to connect Adikteev 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 Adikteev with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent churn analysis

Stop trying to make one agent do everything. With CrewAI, you assign distinct roles. You build a Data Analyst agent that specifically runs `get_churn_scores` to monitor your user base. It crunches the numbers and writes a summary of who is about to leave. That summary gets passed through shared memory to a Marketing Strategist agent. This second agent reads the findings and uses `create_segment` to build a highly targeted retention audience. They work together sequentially, just like a real marketing team.

Autonomous Adikteev MCP Server reporting

Tracking ad spend takes constant supervision. You can set up a Monitor agent that runs on a schedule, calling `get_reporting` to check how your retargeting campaigns are performing on the Adikteev MCP Server. It looks for anomalies in the conversion rates or spend. If performance drops, it alerts a Moderator agent. This setup gives you hands-free oversight. The crew watches the metrics, flags issues, and keeps marketing operations running without you having to pull a single report manually.

Hierarchical campaign management

Complex marketing tasks require a boss. You can run your crew in hierarchical mode, where a Manager agent delegates tasks to worker agents. The manager might ask one worker to find the correct account using `list_companies`. Once the ID is secured, the manager tells another worker to check existing audiences via `list_segments`. The manager runs the entire process from the top down. You just give the team a goal, and it figures out which MCP tools to use.

Setup guide

Set up Adikteev 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 Adikteev tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Run `pip install crewai "crewai[tools]"`. For a basic setup, just drop your Vinkius URL into the `mcps` array on your Agent definition.

Yes. CrewAI relies on shared memory. One agent can pull campaign performance stats, and a completely different agent can read that exact data to make routing decisions.

Import `MCPServerHTTP` from `crewai.mcp` and use the `tool_filter` argument. You can give your analyst agent access to reporting tools while restricting segment creation to your manager agent.

You can structure your crew to run tasks in a strict order. The first agent grabs the churn metrics, finishes its job, and hands the output directly to the second agent for audience building.

Vinkius handles the security layer. Every time your crew pulls campaign performance or user lists, the request hits a zero-trust sandbox. The connection is authenticated via a single endpoint token, keeping your credentials off the local machine.

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