How to Use the Ecomail MCP in OpenAI Agents SDK

Q: How do I connect the Ecomail MCP Server to the OpenAI Agents SDK?

Pass it directly to the agent constructor. Initialize MCPServerStreamableHttp with your Vinkius endpoint URL, then add it to the mcpservers array. The SDK handles tool discovery automatically.

Q: Can the OpenAI Agents SDK read my Ecomail templates?

Yes. The agent can call listemailtemplates to read your available message layouts. You can use this data to have the agent draft new copy that fits your existing HTML structures.

Build production-ready email marketing agents with the OpenAI Agents SDK and Ecomail.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ecomail MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect OpenAI Agents SDK to Ecomail

Your production agent needs to read campaign data without breaking its guardrails. By handing it the `ecomail-mcp` server, you give your OpenAI agent direct read access to your email marketing backend. It auto-discovers tools like `list_email_marketing_campaigns` and maps them into its execution loop. Tracing works out of the box. When your agent calls `get_campaign_performance_details` to pull open rates, that request shows up in your OpenAI dashboard. You see exactly what data the agent read before it decided to generate a new follow-up sequence.

Audit subscriber lists autonomously

Stop exporting CSVs to figure out who opened your last broadcast. Your agent can run `list_address_list_subscribers` to pull the raw contact data directly into its context window. If it spots an anomaly, it can drill down to investigate the specific user. It does this by chaining tools. The agent might start with `search_marketing_subscribers` to find a specific record, then immediately fire `get_subscriber_profile` to check their entire click history. You build the handoff logic; the MCP Server handles the API plumbing.

Monitor campaign volume at scale

Rate limits and account caps usually break autonomous agents. We expose `get_ecomail_account_metadata` so your system knows its boundaries before it starts pulling heavy reports. This prevents unexpected crashes during large data extraction runs. For daily reporting routines, your agent can hit `quick_marketing_volume_audit` to grab a high-level summary. Set `cacheToolsList=True` in your setup, and the agent skips the discovery phase on subsequent runs, dropping latency when polling for new campaign metrics.

Setup guide

Set up Ecomail 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 Ecomail tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Ecomail 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="Ecomail Agent",
            instructions="You have access to Ecomail 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 Ecomail. 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 Ecomail 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 Ecomail MCP in OpenAI Agents SDK

Pass it directly to the agent constructor. Initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL, then add it to the `mcp_servers` array. The SDK handles tool discovery automatically.

Yes. The agent can call `list_email_templates` to read your available message layouts. You can use this data to have the agent draft new copy that fits your existing HTML structures.

It does. Every tool execution passes through your defined safety constraints. If the agent tries to pull 50,000 records via `list_latest_marketing_campaigns` and violates a token limit rule, the SDK blocks the call.

The server returns an error code to the agent. Because you are using a production SDK, you can write fallback logic or trigger a human handoff when the agent fails to fetch a subscriber profile.

The server processes raw subscriber email addresses and click histories in a V8 Isolate Sandbox. This environment is ephemeral and destroys itself after the agent finishes the request. No contact records are written to disk or retained after the session ends.

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