How to Use the Mautic MCP in OpenAI Agents SDK

Q: How do I set up the Mautic MCP Server with OpenAI Agents SDK?

Install the package using pip install openai-agents. Initialize the server with MCPServerStreamableHttp pointing to your Vinkius endpoint, then pass it to your Agent constructor in the mcpservers list.

Q: How does the OpenAI Agents SDK cache Mautic tool lists?

Set cacheToolsList=True in your agent configuration. This stops the SDK from querying the server for tool definitions on every single run, speeding up calls to listcontacts and createcontact.

Q: How do handoffs work in OpenAI Agents SDK when managing Mautic segments?

You can build one agent to search contacts using listcontacts and another to assign them via addcontacttosegment. The OpenAI Agents SDK manages the state handoff between them without losing the contact context.

Run production-grade marketing campaigns directly from OpenAI Agents SDK without manual API plumbing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mautic MCP to OpenAI Agents SDK

Create your Vinkius account to connect Mautic to OpenAI Agents SDK 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 Mautic with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe lead ingestion via OpenAI Agents SDK

Your agent can create and update leads safely using `create_contact` and `get_contact`. The SDK runs these actions through built-in guardrails, so your agent won't accidentally overwrite critical CRM fields during a customer interaction. If a lead needs complex routing, the SDK handles handoffs between specialized agents. One agent checks the company details with `get_company` while another runs the contact updates, tracking every step in the OpenAI dashboard.

Automated segment routing with MCP Server tools

Let your agent manage list hygiene by running `list_segments` and `add_contact_to_segment` on the fly. When a contact's status changes, the agent moves them to the correct group instantly. Because this MCP Server exposes direct endpoints, your agent doesn't need custom glue code. It queries `list_contacts` to find matches and assigns them to active marketing tracks without human intervention.

Campaign inspection and tracking

Monitor active marketing sequences directly from your python code using this MCP setup. Your agent uses `get_campaign` and `list_campaigns` to pull real-time performance metrics and decide if a lead needs a different approach. You can audit these decisions using the OpenAI tracing dashboard. It logs every call to `get_email` and `list_emails`, showing you exactly which templates your agent selected for each contact.

Setup guide

Set up Mautic MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mautic tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mautic tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mautic tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mautic Agent",
            instructions="You have access to Mautic tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Mautic. 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 Mautic 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 Mautic MCP in OpenAI Agents SDK

Install the package using `pip install openai-agents`. Initialize the server with `MCPServerStreamableHttp` pointing to your Vinkius endpoint, then pass it to your Agent constructor in the `mcp_servers` list.

Set `cacheToolsList=True` in your agent configuration. This stops the SDK from querying the server for tool definitions on every single run, speeding up calls to `list_contacts` and `create_contact`.

You can build one agent to search contacts using `list_contacts` and another to assign them via `add_contact_to_segment`. The OpenAI Agents SDK manages the state handoff between them without losing the contact context.

Yes, you can control tool access at the SDK level. If you only want your agent to read campaign data, expose `list_campaigns` and `get_campaign` while omitting destructive write tools.

Your contact emails and phone numbers are protected by the Vinkius zero-trust sandbox. The server runs in an ephemeral isolate, meaning your Mautic credentials and customer profiles are never stored or exposed to third parties.

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