How to Use the Customer.io MCP in CrewAI

Q: How do I add the Customer.io MCP Server to my CrewAI setup?

Install crewaitools via pip. For a basic setup, pass your Vinkius endpoint directly into the mcps array on your Agent definition. The crew will automatically discover the available marketing endpoints.

Q: Can CrewAI filter which Customer.io tools an agent sees?

Yes. Use MCPServerHTTP from crewai.mcp and apply a toolfilter. You can give your analyst agent access to reporting tools while restricting the identifycustomer mutation tool to a specific moderator agent.

Q: Do CrewAI agents share Customer.io context?

Shared memory is a core feature. If Agent A runs listnewsletters and finds a failed campaign, Agent B can read that context and investigate the specific newsletter ID without needing to fetch the list again.

Deploy a crew of specialized Python agents to autonomously monitor and manage your Customer.io marketing campaigns.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Customer.io MCP to CrewAI

Create your Vinkius account to connect Customer.io 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 Customer.io with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Campaign Monitoring

Assigning a CrewAI monitoring agent to run `get_campaign_performance` automates your schedule. Stop checking dashboards manually. The Python agent evaluates sent, opened, clicked, and converted counts against your target baselines. Flagging issues in shared memory happens when engagement drops below a threshold. A secondary analyst agent then picks up the context and runs `get_engagement_summary`. This checks if the global analytics boundary shows a broader delivery problem.

Customer.io MCP Server Crew

Calling `list_customer_segments` maps out your dynamic lists through a specialized worker agent. Managing audiences requires careful coordination. Set up a hierarchical crew where the manager agent delegates tasks to specialists. Executing `list_customers` pulls unique identifiers and last-seen timestamps via another worker. CrewAI agents share memory natively. The manager synthesizes this data from the Customer.io MCP Server to recommend audience pruning without any human intervention.

Profile Resolution Pipelines

Firing `search_customers_by_email` finds the exact profile when a researcher agent takes an incoming ticket. Customer support operations move faster when agents handle the lookup. The resulting identifiers get passed down the execution chain. Running `get_customer_details` resolves the custom attributes and device tokens instantly. The next agent in line uses those inherited identifiers to execute the tool. By the time your human team looks at the escalation, the crew has already built a complete behavioral profile.

Setup guide

Set up Customer.io 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 Customer.io tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Install crewai[tools] via pip. For a basic setup, pass your Vinkius endpoint directly into the mcps array on your Agent definition. The crew will automatically discover the available marketing endpoints.

Yes. Use MCPServerHTTP from crewai.mcp and apply a tool_filter. You can give your analyst agent access to reporting tools while restricting the identify_customer mutation tool to a specific moderator agent.

Shared memory is a core feature. If Agent A runs list_newsletters and finds a failed campaign, Agent B can read that context and investigate the specific newsletter ID without needing to fetch the list again.

The framework supports stdio, SSE, and Streamable HTTP. Vinkius provides a standard HTTP endpoint, so your Python agents can connect over the network without managing local server processes.

This implementation exposes email addresses, behavioral data, and global analytics. Vinkius isolates every single tool call in a dedicated runtime. No external processes can access the memory space, and the container destroys itself the moment the Python client receives the payload.

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