How to Use the UniOne MCP in CrewAI

Q: How do I list available email templates using UniOne and CrewAI?

Your crew agent calls the listtemplates tool. This immediately gives the team a comprehensive list of all template names, allowing them to decide which content assets are ready for deployment.

Q: What does UniOne provide regarding webhooks for CrewAI?

You can first map out all current connections by calling listwebhooks. For deep inspection, the agent uses getwebhook to pull specific configuration details. This helps ensure autonomous operations hit the right endpoints.

Q: How do I initiate an email send using UniOne and CrewAI?

Sending is simple: use sendemail for immediate, one-off messages. For anything that uses structured content or marketing material, the team uses sendtemplate.

Automate complex email operations with CrewAI and UniOne's MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect UniOne MCP to CrewAI

Create your Vinkius account to connect UniOne 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 UniOne with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Email Content Availability

The crew can start by checking available content. Use `list_templates` to get a master list of all email templates the team knows about. This initial research step prevents wasted effort. Once the template exists, specialized agents can pull details using `get_template`. If the data is bad or missing, another agent can flag it for manual review.

Manage and Verify Webhook Connections

For autonomous operations, webhooks are key. A monitoring agent starts by calling `list_webhooks` to map out every existing connection. To verify the setup, the team calls `get_webhook`, confirming the endpoint is ready. If a new system needs integration, another specialized agent uses `set_webhook` to configure it and reports back on success.

Perform Transactional and Bulk Sends

The core action: sending emails. The crew can trigger a simple message with `send_email`, or execute complex marketing sends using `send_template`. These actions are wrapped in the workflow logic. Crucially, before any send, the team should check `list_suppression` to ensure they aren't targeting known bad addresses.

Setup guide

Set up UniOne 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 UniOne tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Your crew agent calls the `list_templates` tool. This immediately gives the team a comprehensive list of all template names, allowing them to decide which content assets are ready for deployment.

You can first map out all current connections by calling `list_webhooks`. For deep inspection, the agent uses `get_webhook` to pull specific configuration details. This helps ensure autonomous operations hit the right endpoints.

Sending is simple: use `send_email` for immediate, one-off messages. For anything that uses structured content or marketing material, the team uses `send_template`.

Yes. The crew can add addresses to the block list by calling `set_suppression`. To confirm what's already blocked, they run `list_suppression`.

This MCP Server manages three main data types: email templates (content definitions), webhooks (external endpoints), and suppression lists (bounced/blocked addresses).

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