How to Use the Todoist MCP in OpenAI Agents SDK

Q: What if I need to check project structure with Todoist using the OpenAI Agents SDK?

You can run listprojects first, then follow up by calling listprojectsections. This lets your agent map out the entire hierarchy of a single project. It’s how you verify that all sections are accounted for.

Q: Can Todoist handle complex searches with the OpenAI Agents SDK?

Absolutely. The listactivetasks tool allows filtering by label, project, or a specific filter string. You can tell your agent to narrow down thousands of tasks right to the handful that matter today.

Q: How do I manage tasks that were closed in Todoist using the OpenAI Agents SDK?

Use the reopentask tool. If a project item got accidentally marked as finished, this function brings it back to active status for your agent to work on.

Finish your to-do list faster with the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Todoist MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Keep track of all projects in Todoist.

Start by calling `list_projects` to pull a full manifest of every project you've set up. This gives your agent a clear map of where everything lives, so it knows exactly what data pool it's working with. You can then dive deeper using `get_project_details`. It pulls the metadata for any given project, letting your agent understand the context—is this a work project or personal stuff? That detail is key.

Update tasks and mark them done.

Need to change a task's status or details? The `update_task_details` tool modifies existing items directly. You can adjust descriptions, due dates, or anything else that needs fixing. Don't forget the finish line: use `complete_task` to mark a job as done. This gives your agent the ability to officially close out tasks when they're finished.

Check details and list active work.

The `list_active_tasks` function filters what you need, letting your agent pull only items by project, label, or a specific filter. It doesn’t dump the whole to-do list on you; it shows the relevant stuff. Want to see *everything*? Use `get_task_details` for a deep dive into one item, or call `list_all_labels` if your agent needs to know what tagging system is in play.

Setup guide

Set up Todoist 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 Todoist tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent uses the MCP Server tools directly. You simply pass the server endpoint to your Agent constructor, and it auto-discovers all 12 available functions. It's built for production use, so you get guardrails validation before any action runs.

You can run `list_projects` first, then follow up by calling `list_project_sections`. This lets your agent map out the entire hierarchy of a single project. It’s how you verify that all sections are accounted for.

Absolutely. The `list_active_tasks` tool allows filtering by label, project, or a specific filter string. You can tell your agent to narrow down thousands of tasks right to the handful that matter today.

It touches task metadata, project names, labels, and user-defined descriptions. Specifically, it handles task status updates via `complete_task`.

Use the `reopen_task` tool. If a project item got accidentally marked as finished, this function brings it back to active status for your agent to work on.

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