How to Use the Emarsys MCP in CrewAI

Q: How do I give different CrewAI agents access to different Emarsys tools?

When you initialize the MCPServerHTTP object in CrewAI, use the toolfilter argument. This lets you create separate server instances for each agent, exposing only the tools relevant to their role, like giving an Analyst agent getcampaigndetails but not the Monitor.

Q: Can a CrewAI crew build a report on my Emarsys account?

Yes. You could have one agent use getemarsysaccountmetadata for account info, a second agent use listemailcampaigns for a campaign inventory, and a final agent to compile the data from shared memory into a summary.

Deploy autonomous agent crews to monitor and manage your Emarsys marketing operations 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 Emarsys MCP to CrewAI

Create your Vinkius account to connect Emarsys 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 Emarsys with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Operations Crew

Assemble a team of agents to run your Emarsys account. Assign one agent the 'Monitor' role. Its job is to periodically run a `quick_engagement_volume_audit` and pass the results to the crew's shared memory. A second 'Analyst' agent can then pick up that data. If it detects an anomaly, it can dig deeper using `list_email_campaigns` and `get_campaign_details` to find the root cause. This division of labor is what makes CrewAI powerful.

Segment Intelligence Team

You don't just get a list of segments; you get insights. Have a 'Researcher' agent use `list_audience_segments` and `list_marketing_contact_lists` to gather raw data. It passes this inventory to the next agent in the hierarchy. The 'Strategist' agent takes over, cross-referencing lists and segments to find overlaps or gaps. It can even check which `list_trigger_events` are tied to which segments, identifying opportunities for new automation programs.

Your Emarsys MCP Server Crew

A 'Compliance' agent can be tasked with maintaining an inventory of all customer-facing assets. It uses `list_registration_forms` to make sure all data capture points are documented and accounted for. Meanwhile, an 'Orchestrator' agent keeps a master list of all workflows by calling `list_automation_programs`. The crew works together, sharing context to provide a complete picture of your Emarsys setup without any manual checks.

Setup guide

Set up Emarsys 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 Emarsys tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

When you initialize the `MCPServerHTTP` object in CrewAI, use the `tool_filter` argument. This lets you create separate server instances for each agent, exposing only the tools relevant to their role, like giving an Analyst agent `get_campaign_details` but not the Monitor.

Yes. You could have one agent use `get_emarsys_account_metadata` for account info, a second agent use `list_email_campaigns` for a campaign inventory, and a final agent to compile the data from shared memory into a summary.

For a simple setup, just pass the Vinkius URL with your token directly into the `mcps` list when defining your Agent. CrewAI will automatically discover and register all the available Emarsys tools.

Exactly. That's the core workflow. An agent in a 'sequential' crew could use `list_email_campaigns` in the first task. The next agent in the crew gets the output of that task as context and can then use `get_campaign_details` to investigate specific campaigns from the list.

The server only exposes metadata like campaign IDs, segment names, and automation program structures. Your actual customer contact data is never touched. Each CrewAI agent interacts with the Vinkius endpoint, which runs in a zero-trust, ephemeral environment, ensuring that access to your Emarsys metadata is isolated and secure.

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