How to Use the AdRoll MCP in CrewAI

Q: Can I build a team of agents to monitor AdRoll with CrewAI?

Absolutely. You can create a "Monitor" agent that uses getperformancereport and a "Notifier" agent that sends alerts. They collaborate using CrewAI's framework to provide autonomous monitoring for your AdRoll campaigns.

Q: How does CrewAI handle multiple AdRoll accounts?

A lead agent can use listadvertisables to get all your accounts, then create and delegate tasks to other agents in the crew, one for each AdRoll account. It's a very efficient way to parallelize work across your whole client base.

Q: Can I limit which AdRoll tools a specific CrewAI agent can use?

Yes. If you use the MCPServerHTTP class for setup, you can use the toolfilter argument. This lets you expose only specific tools, like listcampaigns, to a certain agent, enforcing role separation.

Deploy a crew of AI agents to manage your AdRoll account. Automate monitoring, analysis, and reporting with CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdRoll MCP to CrewAI

Create your Vinkius account to connect AdRoll 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 AdRoll with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Set Up an AdRoll Watchdog Crew

This is exactly what CrewAI was built for. Assign one agent the role of "Campaign Monitor" and have it periodically run `list_campaigns` and `get_performance_report`. A second agent, the "Performance Analyst," grabs that data from the crew's shared memory. Its goal is to spot anomalies. If it finds a campaign with a sudden drop in CTR, it passes the task to a third agent to fire off an alert.

Delegate Reporting Across Clients

For agencies, this is a game-changer. A lead "Account Manager" agent uses `list_advertisables` to get a list of all your clients. It then delegates tasks to a pool of "Reporting" agents. Each one takes an advertiser ID, pulls all the relevant data using `get_campaign_details` and `get_performance_report`, and formats a summary. They work in parallel, so the whole job gets done fast. This MCP Server makes that whole process possible.

Analyze Ad Creatives at Scale

Use the `list_ads` tool to give your CrewAI agents a full inventory of your ad creatives. An "Analyst" agent can then correlate ad details with performance data from `get_performance_report`. The goal is to find patterns an individual might miss. A "Strategist" agent can then take those findings to generate new ideas, like "Video ads are outperforming static images for campaign X." Your crew works together to turn raw data into actual insights.

Setup guide

Set up AdRoll 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 AdRoll tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The easiest way is to pass your Vinkius MCP URL directly into the `mcps` list when you define an Agent. CrewAI handles the connection and makes the AdRoll tools available to that agent automatically.

Absolutely. You can create a "Monitor" agent that uses `get_performance_report` and a "Notifier" agent that sends alerts. They collaborate using CrewAI's framework to provide autonomous monitoring for your AdRoll campaigns.

A lead agent can use `list_advertisables` to get all your accounts, then create and delegate tasks to other agents in the crew, one for each AdRoll account. It's a very efficient way to parallelize work across your whole client base.

Yes. If you use the `MCPServerHTTP` class for setup, you can use the `tool_filter` argument. This lets you expose only specific tools, like `list_campaigns`, to a certain agent, enforcing role separation.

Your data is only in transit between the AdRoll API and your agent. This MCP server processes AdRoll campaign details and performance reports inside an ephemeral, zero-trust sandbox, with the connection secured by your unique Vinkius token. Nothing is ever logged or stored.

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