How to Use the Unbounce MCP in CrewAI

Q: What data types does Unbounce touch with CrewAI?

The scope covers everything from account listings (listaccounts) down to individual form fields (listformfields). All these structured datasets become available for the collaborative agents.

Q: If I need to check Unbounce domains, how does CrewAI manage it?

You assign the listdomains tool to a specific agent's toolkit. That agent executes the call, and its findings are then available for other specialized agents in the crew to analyze.

Run specialized teams of agents across Unbounce tasks with CrewAI's collaborative MCP Server framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unbounce MCP to CrewAI

Create your Vinkius account to connect Unbounce 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 Unbounce with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Lead Research and Retrieval

You assign roles: Agent A researches the market, and Agent B retrieves data. Agent B uses `get_lead` to pull specific lead details for analysis. CrewAI manages this collaboration. The shared memory allows Agent A's findings to inform Agent B's tool calls against the MCP Server.

Team-Based Account Monitoring

Set up a monitoring crew: one agent lists all accounts (`list_accounts`), and another validates those results by calling `get_me`. The moderator agent watches both sessions. This sequential execution allows you to build highly sophisticated operational pipelines, mimicking human team handoffs.

Orchestrate Page Building Operations

A multi-agent crew can tackle page creation. One agent uses `list_page_groups` to define the scope, and a second agent uses `get_page` to fetch existing details for comparison. This hierarchical execution models real collaboration—the team plans first, then executes specialized tasks using the MCP Server.

Setup guide

Set up Unbounce 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 Unbounce tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

CrewAI treats the MCP Server as a pool of tools for its agents. You define roles, and those roles are equipped with access to functions like `list_pages` or `get_page`. The agents then collaborate autonomously.

Yes. Because of shared memory, you can build workflows where Agent A gathers a list (e.g., using `list_sub_accounts`) and passes that structured output to Agent B for subsequent actions.

For simple setups, pass the MCP Server URL directly. For more control, use `tool_filter` when initializing the server connection so only necessary tools are exposed to specific agents.

The scope covers everything from account listings (`list_accounts`) down to individual form fields (`list_form_fields`). All these structured datasets become available for the collaborative agents.

You assign the `list_domains` tool to a specific agent's toolkit. That agent executes the call, and its findings are then available for other specialized agents in the crew to analyze.

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