How to Use the Sunsama MCP in OpenAI Agents SDK

Q: What is the process for deleting tasks with Sunsama using the OpenAI Agents SDK?

You can use deletetask when you know a task is obsolete. Be careful, though; this action is irreversible. The agent validates your request before finalizing any deletion.

Q: Can I check my user details in Sunsama using the OpenAI Agents SDK?

Yeah, of course. You use getuserprofile to pull your current profile information into your agent system. This is useful for tracking who owns specific tasks or project channels.

Manage your daily work in Sunsama using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Sunsama MCP to OpenAI Agents SDK

Create your Vinkius account to connect Sunsama to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Sunsama with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

List all tasks with `list_tasks`

The agent retrieves every task across your workspace. You can filter these results by date, letting your AI client pinpoint exactly what needs attention today. This function ensures that the whole project picture is visible before any action is taken. It’s perfect for an initial status check or building a list of dependencies.

Create new tasks with `create_task`

Need to log a quick thought? Your agent builds and assigns the task using `create_task`. You just send the text and maybe an optional due date, and it’s added instantly. This is how you keep momentum going. The built-in guardrails make sure the task gets created correctly before your workflow moves on.

Update project information with `update_task`

If a deadline shifts or details change, the agent handles it via `update_task`. You just specify the ID and the new text, and the task gets corrected. It’s straightforward. The system doesn't mess up existing tasks; it overwrites only what you tell it to. This keeps your project records clean and accurate.

Setup guide

Set up Sunsama 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 Sunsama tools at runtime.
3

Create your Agent

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

Run the agent

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

The agent connects directly, treating Sunsama like a managed resource. You tell it to list tasks or create one, and it executes that command safely via its built-in guardrails.

You can use `delete_task` when you know a task is obsolete. Be careful, though; this action is irreversible. The agent validates your request before finalizing any deletion.

Yeah, of course. You use `get_user_profile` to pull your current profile information into your agent system. This is useful for tracking who owns specific tasks or project channels.

The unique power of this MCP Server setup is its built-in validation. If an agent action hits a snag—like invalid text for `create_task`—the guardrails catch it immediately. You get clear feedback, not just a silent failure.

This MCP Server touches task details (text and dates), user profiles, channels, and contexts. The agent validates all these pieces of information before executing any write operation.

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