How to Use the GrowingIO MCP in CrewAI

Run autonomous multi-agent teams that coordinate analytics audits and campaign monitoring with CrewAI and GrowingIO.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GrowingIO MCP to CrewAI

Create your Vinkius account to connect GrowingIO 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 GrowingIO with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Multi-Agent Analytics Audits

The `list_variables` tool lets your tracking auditor agent inspect your active data schema while an analyst agent uses `list_log_sources` to verify incoming data streams. Together, these CrewAI agents cross-reference tracked variables against active logs to spot missing events. By dividing the work, the crew can analyze your entire tracking setup without manual oversight. One agent flags the missing variables, another checks the project metadata via `get_project_info`, and a third generates a clean markdown report.

Autonomous Funnel and Segment Monitoring

The `get_funnel` tool is used by your monitoring agent to track conversion health, while a separate marketer agent queries `list_segments` to find underperforming cohorts. The agents share context in memory to match funnel drop-offs with specific user segments. This collaborative approach means your CrewAI team doesn't just look at isolated numbers. They synthesize funnel performance and segment sizes to tell you exactly which group of users is abandoning your signup flow.

AI-Driven Ad Campaign Optimization with MCP Server

The `list_ads` tool allows your media buyer agent to pull active campaign lists, which it then hands off to an optimization agent running `get_metrics` to calculate ROI. The agents collaborate to decide which campaigns need budget adjustments. Using this MCP Server with CrewAI lets you set up an autonomous marketing desk. The agents run on a loop, constantly checking campaign performance and preparing budget recommendations without you lifting a finger.

Setup guide

Set up GrowingIO 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 GrowingIO tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

CrewAI agents use their shared memory system to pass outputs from tools like `get_metrics` or `list_segments` between the researcher and the analyst agents during a run.

Yes. You can use the MCPServerHTTP tool filter to expose only `list_ads` to your marketing agent, while keeping sensitive tools like `get_segment_users` restricted to your admin agent.

No. You can pass your Vinkius MCP Server URL directly into the CrewAI agent configuration, allowing your team to start calling `list_events` with minimal boilerplate.

Yes. You can appoint a manager agent to oversee the execution, directing subordinate agents to fetch funnel details or event logs as needed to solve a complex analytical query.

The GrowingIO MCP Server processes all event logs and variable metadata through ephemeral V8 isolates. No data is stored, and Vinkius uses strict network isolation to guarantee your analytics data never leaks between agent sessions.

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