How to Use the Amazing Marvin MCP in OpenAI Agents SDK

Q: How do I connect Amazing Marvin to my OpenAI Agents SDK pipeline?

Install the SDK and register the MCP server using MCPServerStreamableHttp with your Vinkius endpoint. Pass the server in the mcpservers list when instantiating your agent. Turn on cacheToolsList=True to keep tool discovery fast and avoid unnecessary network calls.

Q: How does Amazing Marvin handle task assignment conflicts in OpenAI Agents SDK?

The agent uses updatetask to resolve conflicts by updating dates or titles directly. The MCP Server returns the updated status, allowing your agent to gracefully log the state and move to the next item in its queue.

Give your OpenAI Agents SDK production deployment direct control over your Amazing Marvin task lists and schedules.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Amazing Marvin MCP to OpenAI Agents SDK

Create your Vinkius account to connect Amazing Marvin 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 Amazing Marvin with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated time tracking with built-in guardrails

Using `start_tracking` and `stop_tracking`, your agent can control the Marvin clock automatically. When a task starts, the agent spins up Marvin's timer, and halts it when the work wraps up. Because you are using OpenAI's production framework, you can set strict validation gates to ensure your agent never leaves a timer running indefinitely or tracks time on the wrong ticket. Once the job is done, the agent completes the loop by triggering `mark_done`. This keeps your billing and productivity records clean without you ever opening the Marvin web app.

Structuring task hierarchies via the MCP Server

Building workspace structures relies on `add_category` and `add_project` to organize your inbox. Your agent can build out your entire workspace structure on the fly based on incoming emails or Slack requests. It reads existing layouts using `get_children` to find where new items belong, avoiding duplicate folders. This setup lets you delegate the boring work of organizing client deliverables. The agent maps your complex project trees directly into Marvin using this MCP Server connection, keeping your workspace structured.

Dynamic schedule management

Retrieving daily agendas via `get_today_items` allows your agent to plan your schedule. The agent pulls your scheduled agenda, compares it with your calendar, and uses `add_task` to insert missing high-priority items. If priorities shift mid-day, the agent relies on `update_task` to reschedule items or edit titles. You get an organized day without manually dragging tasks around.

Setup guide

Set up Amazing Marvin 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 Amazing Marvin tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and register the MCP server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server in the `mcp_servers` list when instantiating your agent. Turn on `cacheToolsList=True` to keep tool discovery fast and avoid unnecessary network calls.

Yes, the SDK's built-in guardrails let you inspect tool arguments before execution. When the agent tries to run `start_tracking` or `stop_tracking`, your code can validate the task ID first. This prevents the agent from starting timers on archived or incorrect tasks.

The agent uses `update_task` to resolve conflicts by updating dates or titles directly. The MCP Server returns the updated status, allowing your agent to gracefully log the state and move to the next item in its queue.

This MCP integration runs over a secure HTTP stream managed by Vinkius. You connect your agent using the streamable HTTP class, allowing your production system to run serverless without maintaining persistent WebSocket connections.

Your task titles, project structures, and tracked time logs are protected by Vinkius's zero-trust sandboxed architecture. Every request goes through a single-token secure endpoint, ensuring your personal productivity data is never exposed to public networks or cached outside your execution context.

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