How to Use the Gmelius MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle agent handoffs for Gmelius email triage?

You define specialized agents—one for reading emails via listgmeliusconversations and another for board management. The SDK manages the transition, passing the active conversation ID between them to execute complex inbox workflows.

Build production-ready agents using OpenAI Agents SDK that interact with Gmelius shared inboxes and boards.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gmelius MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Email Workflows via OpenAI Agents SDK

The `list_gmelius_conversations` tool exposes raw Gmail threads directly to your OpenAI Agents SDK runtime. Feeding these shared inbox threads into your agentic loops allows the SDK to automatically parse incoming messages and track runs on the OpenAI dashboard. When your agent decides to delegate a task, it invokes `get_gmelius_conversation` to fetch the specific email history. The built-in guardrails in your OpenAI Agents SDK validate these fetched threads before execution, ensuring no raw data leaks back to your shared Gmelius workspace.

Control Gmelius Boards with Guardrails

The `list_gmelius_boards` tool lets your OpenAI Agents SDK inspect active team boards and locate bottlenecked tasks. You configure your OpenAI agent to track these boards using our MCP Server, allowing specialized agents to handle handoffs when transitioning from email triage to board updates. Your agent uses `create_gmelius_card` to insert new tasks directly onto the team's visual board. Because the OpenAI Agents SDK forces schema validation, your agent only writes well-formed cards to your collaborative Gmelius workspace.

Standardize Templates and Sequences

The `list_gmelius_templates` tool retrieves your team's pre-approved email templates directly into your OpenAI Agents SDK runtime. Your OpenAI agent matches customer inquiries against these templates, ensuring a consistent brand voice without writing raw replies from scratch. To automate outreach, the agent uses `list_gmelius_sequences` to verify which follow-up tracks are active in Gmelius. The OpenAI dashboard traces these tool calls in real-time, giving your ops team complete visibility into how the agent manages your shared inbox.

Setup guide

Set up Gmelius 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 Gmelius tools at runtime.
3

Create your Agent

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

Run the agent

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

You install the SDK and initialize the MCP Server streamable HTTP transport pointing to your Vinkius endpoint. The OpenAI Agents SDK automatically discovers the 9 Gmelius tools, exposing them to your agent constructor without manual schema definitions.

Yes. You can write custom interceptors in Python that inspect arguments for tools like `create_gmelius_card` before they execute. This prevents your agent from creating duplicate or malformed cards on your shared boards.

You define specialized agents—one for reading emails via `list_gmelius_conversations` and another for board management. The SDK manages the transition, passing the active conversation ID between them to execute complex inbox workflows.

Your agent script catches the connection error during the status check and can trigger a graceful fallback. This prevents the agent from attempting to read or write to your shared boards during unexpected downtime.

The server only touches the specific email threads, templates, and board cards you authorize. All payload data passes through ephemeral V8 isolates on Vinkius, meaning your raw Gmail messages are never stored or used to train OpenAI models.

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