How to Use the Elastic Email MCP in OpenAI Agents SDK

Q: How do I install the Elastic Email MCP Server for OpenAI Agents SDK?

Run pip install openai-agents. You initialize MCPServerStreamableHttp with your Vinkius endpoint URL and pass it to your Agent constructor. Set cacheToolsList=True to speed up tool discovery.

Q: Can OpenAI Agents SDK read my Elastic Email templates?

Yes. The listemaildesigns tool returns your available message templates. Your agent can read these designs to suggest content updates or verify formatting.

Q: Does the agent know my Elastic Email account limits?

It does if you ask it. The getelasticemailmetadata tool pulls your current usage limits. You can write a guardrail that blocks the agent from acting if the quota is low.

Q: How do I check bounce rates using Elastic Email and OpenAI Agents SDK?

Your agent calls listdeliverylogs to get recent delivery statuses. It can filter this data to find hard and soft bounces, then pass the results to a reporting agent.

Give your OpenAI Agents SDK production-ready access to your Elastic Email campaigns and delivery logs.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Elastic Email MCP to OpenAI Agents SDK

Create your Vinkius account to connect Elastic Email 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 Elastic Email with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Campaigns with OpenAI Agents SDK

The `get_campaign_performance` tool pulls hard numbers on your latest email sends directly into your Python agent context. You don't guess if an email worked. You look at the open rates, clicks, and bounce metrics. Your agent uses `list_marketing_campaigns` to grab the historical backlog. If a campaign tanks, the agent can trigger a handoff to a specialized analysis agent to figure out why, all tracked in your OpenAI dashboard.

Monitor Delivery Constraints

The `list_delivery_logs` tool exposes the exact status of every outgoing message. When a user complains about missing a password reset, your agent checks the logs instantly via this MCP Server. Pair this with `get_elastic_email_metadata` to keep an eye on your usage limits. You can build guardrails that prevent your agent from triggering massive sends if you are close to your account cap.

Query Contact Profiles

The `search_contacts_by_email` tool finds individual subscribers across your entire database. It takes a single email address and returns the matching record. Once you find the target, `get_contact_profile` fetches their complete engagement history. This MCP Server lets your agent build a full picture of a subscriber before deciding how to interact with them.

Setup guide

Set up Elastic Email 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 Elastic Email tools at runtime.
3

Create your Agent

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

Run the agent

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

Run `pip install openai-agents`. You initialize `MCPServerStreamableHttp` with your Vinkius endpoint URL and pass it to your Agent constructor. Set `cacheToolsList=True` to speed up tool discovery.

Yes. The `list_email_designs` tool returns your available message templates. Your agent can read these designs to suggest content updates or verify formatting.

It does if you ask it. The `get_elastic_email_metadata` tool pulls your current usage limits. You can write a guardrail that blocks the agent from acting if the quota is low.

Your agent calls `list_delivery_logs` to get recent delivery statuses. It can filter this data to find hard and soft bounces, then pass the results to a reporting agent.

This integration accesses raw contact profiles and delivery logs. Vinkius runs the MCP Server in an ephemeral V8 Isolate Sandbox. The process spins up, executes the tool call, and dies immediately, leaving zero persistent state behind.

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