Can I filter tasks for today using the AI?

Yes! Use the `list_active_tasks` tool and provide the `filter` parameter set to 'today'. Your agent will retrieve all tasks scheduled for the current date.

How do I add a new task to a specific project?

Use the `create_task` tool. Provide the content and the unique Project ID. You can also include a `due_string` like 'tomorrow at 10am' to set a deadline.

Is it possible to list all my labels via AI?

Absolutely. Run the `list_all_labels` query. The agent will retrieve the complete directory of labels you use to categorize tasks in your account.

INSTANT PLUG AND PLAY

Todoist MCP Server for OpenAI Agents SDKGive OpenAI Agents SDK instant access to 12 tools to Complete Task, Create Project, Create Task, and more

Name: Todoist
Availability: InStock
Author: Vinkius

Built by Vinkius GDPR 12 Tools SDK

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

Use with Your AI Agent

Ask AI about this App Connector for OpenAI Agents SDK

Open in ChatGPT Open in Claude Open in Perplexity

The Todoist app connector for OpenAI Agents SDK is a standout in the Industry Titans category — giving your AI agent 12 tools to work with, ready to go from day one.

Vinkius delivers Streamable HTTP and SSE to any MCP client

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="Todoist Assistant",
            instructions=(
                "You help users interact with Todoist. "
                "You have access to 12 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Todoist"
        )
        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 Todoist MCP Server

Connect your Todoist account to any AI agent and simplify how you organize your life and work through natural conversation.

The OpenAI Agents SDK auto-discovers all 12 tools from Todoist through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Todoist, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Task Control — Create, update, and complete tasks with full support for due dates, priorities, and descriptions.
Project Oversight — List all your projects and manage sections to keep your workflows structured.
Smart Filtering — Query your tasks using Todoist's powerful filter syntax (e.g., 'today', 'p1') via AI.
Categorization — List and manage labels to tag your tasks across different projects.
Collaboration — List comments on tasks and projects to track discussions and notes.
Workspace Maintenance — Reopen completed tasks or fetch detailed metadata for specific to-do items.

The Todoist MCP Server exposes 12 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.

All 12 Todoist tools available for OpenAI Agents SDK

When OpenAI Agents SDK connects to Todoist through Vinkius, your AI agent gets direct access to every tool listed below — spanning task-management, to-do-list, workflow-automation, and more. Every call is secured with network, filesystem, subprocess, and code evaluation entitlements inside a sandboxed runtime. Beyond a simple connection, you get a full AI Gateway with real-time visibility into agent activity, enterprise governance, and optimized token usage.

complete_task

Mark a task as finished

create_project

Create a new project

create_task

Add a new to-do item

get_project_details

Get metadata for a project

get_task_details

Get details for a specific task

list_active_tasks

Can filter by project, label, or filter. List active tasks

list_all_labels

List your personal labels

list_comments

List comments for a task or project

list_project_sections

List sections within a project

list_projects

List your Todoist projects

reopen_task

Mark a closed task as active

update_task_details

Modify an existing task

Connect Todoist to OpenAI Agents SDK via MCP

Follow these steps to wire Todoist into OpenAI Agents SDK. The entire setup takes under two minutes — your credentials stay safe behind the Vinkius.

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 12 tools from Todoist

Why Use OpenAI Agents SDK with the Todoist MCP Server

OpenAI Agents SDK provides unique advantages when paired with Todoist 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

Todoist + OpenAI Agents SDK Use Cases

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

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

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

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

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

Example Prompts for Todoist in OpenAI Agents SDK

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

"What are my high priority tasks for today?"

"Create a task in the 'Work' project: 'Submit expense report' due Friday at 5pm."

"Show me all active tasks with the label '@errand'."

Troubleshooting Todoist MCP Server with OpenAI Agents SDK

Common issues when connecting Todoist 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.

Todoist + OpenAI Agents SDK FAQ

Common questions about integrating Todoist 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.

Can I use multiple MCP servers in one agent?

Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.

Does the SDK support streaming responses?

Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.