Where do I get my Todoist API Token?

You can locate your personal API Token securely via the web application by clicking your profile avatar, going to **Settings**, and selecting the **Integrations** tab. Your token will be visible at the bottom or in a dedicated Developer section. Alternatively, navigate directly to `https://todoist.com/prefs/integrations`.

Can the agent delete projects or workspaces?

No. The integration exclusively lists resources (projects, items, labels) and supports only basic item modifications: creating tasks and marking tasks as completed. Destructive actions on structural settings are not supported.

Can the agent organize my tasks using sub-projects or sections?

Yes. The Todoist integration allows the agent to retrieve project IDs and navigate into their specific sections. When creating a new task, you can explicitly ask the agent to place it within a specific section to keep your work neatly organized.

Todoist MCP Server for OpenAI Agents SDK 7 tools — connect in under 2 minutes

Name: Todoist
Availability: InStock
Author: Vinkius

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

Built by Vinkius GDPR 7 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Todoist through the 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="Todoist Assistant",
            instructions=(
                "You help users interact with Todoist. "
                "You have access to 7 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 bring your daily productivity directly into your chat. View your active tasks, manage projects, and quickly add new items to your workflow entirely through conversational commands without ever needing to open the app.

The OpenAI Agents SDK auto-discovers all 7 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 the Vinkius.

What you can do

Project Management — List all your active project folders, retrieve their specific IDs, and view sections within specific projects
Task Execution — View your complete list of pending tasks and mark them as completed instantly
Create Tasks — Add new items to a specific project or your inbox naturally in plain conversation
Organization — Look up available labels/tags to categorize your work
Collaboration — Read through existing comments to catch up on discussion history for any particular task

The Todoist MCP Server exposes 7 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 Todoist to OpenAI Agents SDK via MCP

Follow these steps to integrate the Todoist 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 7 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

Todoist MCP Tools for OpenAI Agents SDK (7)

These 7 tools become available when you connect Todoist to OpenAI Agents SDK via MCP:

complete_task

Marks a task as completed

create_task

Provide content and an optional project ID. Creates a new task in Todoist

list_comments

Lists all comments for a specific task

list_labels

Lists all user-defined labels

list_projects

Lists all active projects in Todoist

list_sections

Lists all sections within a specific project

list_tasks

Can filter by project_id. Lists active tasks, optionally filtered by project

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.

"Check all my active tasks and projects."

"Complete the task with ID 81229."

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.