How to Use the Lunatask MCP in OpenAI Agents SDK

Q: What happens if I call deletetask from my agent?

The deletetask tool removes the task record based on the ID you provide. It's a permanent action, so ensure your agent logic includes proper confirmation steps.

Build production-grade agents in OpenAI Agents SDK that manage your Lunatask workflow without exposing raw sensitive data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lunatask MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated task management for OpenAI Agents SDK

Your agent handles task creation and updates directly. Use `create_new_task` or `update_existing_task` to keep your project status current without leaving the IDE. Everything stays within your defined guardrails. The agent handles the payload and the server ensures your local Lunatask state remains consistent.

Secure habit tracking in your agent loop

Log your daily progress using `track_habit_completion` as part of your agent's routine. It hooks right into your existing automation flow. This keeps your habit data updated without manual entry. Your agent manages the action while you focus on the work.

Metadata-only retrieval for agent context

The server provides `list_tasks_metadata` and `get_task_metadata` so your agent understands project structure. It keeps your raw notes private while letting the agent see what needs attention. Privacy matters. By restricting the MCP Server to metadata, your sensitive journal entries never hit the agent's context window.

Setup guide

Set up Lunatask 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 Lunatask tools at runtime.
3

Create your Agent

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

Run the agent

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

You connect the server as a streamable HTTP resource. The SDK automatically discovers all eight tools, allowing your agent to read metadata and modify tasks immediately.

No. The server only exposes metadata for tasks and notes via `list_notes_metadata`. Raw content remains encrypted locally and never reaches the agent.

It's built for security. Because the API only returns metadata, your private journal entries and task descriptions are never sent to external services.

The `delete_task` tool removes the task record based on the ID you provide. It's a permanent action, so ensure your agent logic includes proper confirmation steps.

Vinkius handles the heavy lifting. You just need your endpoint token to connect the server to your agent environment.

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