How to Use the Adtraction MCP in CrewAI

Q: How do I give a CrewAI agent access to the Adtraction MCP Server?

Pass your Vinkius endpoint string into the mcps array when defining the agent. The crew automatically discovers the available affiliate tools.

Q: Can I restrict which Adtraction tools a CrewAI agent sees?

Use the MCPServerHTTP class from crewai.mcp. You apply a toolfilter so the analyst only sees stats, while the auditor only sees transactions.

Deploy autonomous agent teams in CrewAI to monitor Adtraction affiliate performance 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 Adtraction MCP to CrewAI

Create your Vinkius account to connect Adtraction 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 Adtraction with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Specialized Affiliate Monitoring Crews

Assigning `get_stats_by_program` to a dedicated data analyst agent prevents bottlenecks in your reporting pipeline. One worker tracking everything slows down the whole operation. That persona focuses entirely on pulling daily metrics and identifying performance trends using this MCP Server. A second agent takes those insights and acts on them. The analyst hands off the raw numbers, and the manager writes the weekly partner update.

Autonomous Transaction Audits with CrewAI

Running `list_transactions` through an autonomous monitor agent connected via MCP provides 24/7 fraud detection. It continuously looks for anomalous conversion patterns without human oversight. When the monitor finds something weird, it escalates the issue. A moderator agent receives the flagged record and cross-references it using `list_channels` to verify the traffic source.

Hierarchical Program Management via MCP Server

Calling `list_programs` allows a top-level manager agent to delegate specific campaigns to subordinate workers. Managing dozens of partnerships gets complicated fast. The workload distributes naturally across the crew. Connecting this to your python setup is trivial. You just pass the Vinkius endpoint URL directly into the `mcps` array of your agent definition. The framework handles the underlying HTTP transport automatically.

Setup guide

Set up Adtraction 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 Adtraction tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass your Vinkius endpoint string into the `mcps` array when defining the agent. The crew automatically discovers the available affiliate tools.

Use the `MCPServerHTTP` class from `crewai.mcp`. You apply a `tool_filter` so the analyst only sees stats, while the auditor only sees transactions.

The framework uses shared memory for collaboration. An analyst pulls program details, and the writer agent reads that context to draft an email.

The agents receive the error response and decide how to proceed. You can instruct them to wait and retry or move on to a different task.

The Vinkius zero-trust environment isolates every execution. Your transaction logs and commission payouts process in a temporary V8 sandbox that wipes itself immediately.

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