How to Use the AdButler MCP in CrewAI

Q: How does a CrewAI team analyze AdButler performance?

One agent executes getperformancereport and writes the impressions and clicks to shared memory. A second agent reads those metrics to draft a performance summary.

Deploy autonomous ad operations teams that manage AdButler campaigns using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AdButler MCP to CrewAI

Create your Vinkius account to connect AdButler 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 AdButler with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Performance Reads

`get_performance_report` acts as the primary data source for your analytics agent. This worker pulls raw impressions, clicks, and CTR from the ad network. A separate strategist agent reads that shared memory and formulates recommendations for optimizing the active zones. Running specialized roles prevents context window overload. Passing the Vinkius MCP URL directly into the server array gives your crew instant access to the metrics. The hierarchical execution model forces data to be parsed before the strategist attempts to write a report.

Autonomous Inventory Mapping

`list_publishers` generates a list of partners managing your ad space. Your research agent feeds those IDs into `list_zones` to index every available placement. Another worker cross-references this map against pending self-serve orders. Connecting complex APIs normally requires writing custom Python wrappers. The `MCPServerHTTP` class from the framework manages the transport layer out of the box. Developers simply apply a `tool_filter` to restrict which agents can see the publisher data.

Asset Auditing via MCP Server

`list_campaigns` identifies all active and pending orders in the system. A compliance agent uses `list_creatives` to verify that the required banners and videos actually exist in the library. Missing assets trigger a moderator agent to escalate the issue to a human account manager. Python-based autonomous teams need reliable access to external systems. This MCP connection turns a static ad platform into an interactive environment for your AI workers. They monitor, analyze, and report on self-serve campaigns without human prompting.

Setup guide

Set up AdButler 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 AdButler tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install the framework with the tools extra enabled. Add the Vinkius endpoint URL to your agent configuration to expose the available actions.

You use the built-in HTTP class combined with a tool filter to restrict access. This prevents a reporting agent from accidentally accessing the creative library.

One agent executes `get_performance_report` and writes the impressions and clicks to shared memory. A second agent reads those metrics to draft a performance summary.

The standard MCP protocol handles all tool definitions dynamically. Your workers read the schema at runtime and know exactly how to query campaigns or zones.

Campaign names and asset libraries never reside on shared infrastructure. Vinkius provisions a single-use container for every API interaction. Authentication requires a single endpoint token that you control.

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