Are organizational channels safely isolated when using programmatic executions?

Yes. The AI intrinsically utilizes `list_channels` and `list_contexts` effectively to accurately parse pre-existing frameworks before assignment seamlessly.

Can the agent inadvertently destroy historical tracking via deletion?

The tool bounds the logic reliably using isolated mutation calls like `delete_task`. These are triggered explicitly, protecting chronological historical records systematically effectively internally.

Does the integration sync with external calendars like Google Calendar?

The MCP operates through the Sunsama API, which already consolidates events from Google Calendar, Outlook, and other connected services. Tasks you create or update via the AI will appear alongside your synced calendar events.

Sunsama MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes

Name: Sunsama
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 8 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Sunsama through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Sunsama Assistant",
            instructions=(
                "You help users interact with Sunsama. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Sunsama"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Sunsama MCP Server

Integrate the mindful focus of the Sunsama daily planner directly into your conversational AI environment. Empower your engineering or administrative focus by allowing your LLM to intuitively pull tasks, filter backlog activities, and assign contexts dynamically without constant tab-switching. With this MCP connector attached securely to your workspace, your conversational agent functions as an objective scheduling assistant, seamlessly tracking and resolving your agenda.

The OpenAI Agents SDK auto-discovers all 8 tools from Sunsama through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Sunsama, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Agenda Discovery — Query your scheduled events actively using list_tasks and retrieve deep contextual dependencies of an item utilizing get_task_details.
Task Orchestration — Add new action items seamlessly via create_task or modify ongoing assignments intuitively using update_task.
Taxonomy Mapping — Review your organizational frameworks executing list_channels and list_contexts to accurately file items according to team domains.
Profile Confirmations — Safely extract your user metadata boundaries and operational statuses natively invoking get_user_profile.

The Sunsama MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Sunsama to OpenAI Agents SDK via MCP

Follow these steps to integrate the Sunsama MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 8 tools from Sunsama

Why Use OpenAI Agents SDK with the Sunsama MCP Server

OpenAI Agents SDK provides unique advantages when paired with Sunsama through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Sunsama + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Sunsama MCP Server delivers measurable value.

Automated workflows: build agents that query Sunsama, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Sunsama, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Sunsama tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Sunsama to resolve tickets, look up records, and update statuses without human intervention

Sunsama MCP Tools for OpenAI Agents SDK (8)

These 8 tools become available when you connect Sunsama to OpenAI Agents SDK via MCP:

create_task

Provide text and an optional planned date. Creates a new task in Sunsama

delete_task

This action is irreversible. Permanently deletes a task

get_task_details

Retrieves details for a specific task

get_user_profile

Retrieves the current user profile

list_channels

g., "Work", "Personal"). Lists available Sunsama channels

list_contexts

Lists available Sunsama contexts

list_tasks

You can filter by date. Lists all tasks in Sunsama

update_task

Updates an existing task

Example Prompts for Sunsama in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Sunsama immediately.

"List my tasks for today, complete the design review, and schedule a documentation update for next Monday."

"Read my custom organizational domains running `list_channels` securely, and pull contextual details applying `list_contexts` effectively."

"Verify my identity token evaluating the API user profile comprehensively."

Troubleshooting Sunsama MCP Server with OpenAI Agents SDK

Common issues when connecting Sunsama to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Sunsama + OpenAI Agents SDK FAQ

Common questions about integrating Sunsama MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.