How to Use the Maileroo MCP in CrewAI

Q: How do I stop CrewAI from sending accidental Maileroo emails?

Use the toolfilter parameter. Give your analytical agents access to read-only tools, but strictly reserve the sending tool for a highly restricted dispatch agent.

Q: Will the agents automatically fix broken webhooks?

The agents identify broken routing by calling listconfiguredwebhooks and analyzing the output. They cannot modify the webhooks directly since this toolset only exposes read operations for infrastructure.

Deploy specialized CrewAI agents to monitor, audit, and dispatch your transactional emails autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Maileroo MCP to CrewAI

Create your Vinkius account to connect Maileroo 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 Maileroo with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign a dedicated Maileroo monitor agent

You waste hours checking email delivery dashboards manually. In CrewAI, you assign a specific monitor agent to run `list_sending_activity` every hour. It reads the logs, analyzes bounce patterns, and hands the findings to a reporting agent. This creates a completely autonomous feedback loop. The monitor spots a spike in rejections, passes the context to a technical agent, and that agent investigates the root cause using `get_domain_details`.

Coordinate templates and dispatch

Transactional email requires multiple steps. A research agent gathers the user data, a drafting agent structures the payload, and a dispatch agent executes `send_transactional_email`. They share memory throughout the process. The dispatch agent already knows which layout to use because a previous agent queried the MCP server using `list_email_templates` and stored the correct ID in the crew's shared context.

Audit infrastructure via this MCP Server

Domain settings get messed up when multiple teams touch the same infrastructure. You build a hierarchical CrewAI setup where a manager agent routinely commands workers to verify your setup via `list_sending_domains`. The workers pull the active domains, check the routing rules with `list_configured_webhooks`, and report back. If anything looks wrong, the manager escalates the issue straight to a human operator.

Setup guide

Set up Maileroo 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 Maileroo tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the endpoint directly into your agent's setup using `mcps=["https://..."]`. For tighter control, use `MCPServerHTTP` from `crewai.mcp` and apply a `tool_filter`.

Yes. Your specialized agents share the same MCP connection. One handles log analysis while another prepares payloads for dispatch.

Use the `tool_filter` parameter. Give your analytical agents access to read-only tools, but strictly reserve the sending tool for a highly restricted dispatch agent.

The agents identify broken routing by calling `list_configured_webhooks` and analyzing the output. They cannot modify the webhooks directly since this toolset only exposes read operations for infrastructure.

Your template HTML, variable names, and routing rules pass through a strictly ephemeral sandbox. Vinkius requires exactly one endpoint token to authenticate, and the system retains zero memory of your internal layouts after the agent finishes its task.

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