Todoist MCP: The Official Server at ai.todoist.net
Yes — Todoist has an official MCP server. Doist, the company behind Todoist, hosts it directly at ai.todoist.net/mcp, and it lets any MCP-compatible AI tool read, create, and update your tasks and projects. So if you’re searching “Todoist MCP,” the connection you want already exists and it’s Todoist’s own.
The thing worth knowing before you set it up: an MCP server hands your task list to an AI inside a conversation you start. It’s a doorway, not a worker. Nothing watches Todoist for you, nothing fires when a task comes due, and nothing runs while the chat is closed. Here’s exactly what the Todoist MCP does, how to turn it on, where it stops — and what to use when you want Todoist work that runs on its own.
Todoist is one of many — the complete list of MCP servers covers every app that ships one, grouped by category.
What the Todoist MCP server does
Model Context Protocol (MCP) is the open standard that lets an AI client — Claude, ChatGPT, Cursor, VS Code, and others — talk to an outside app through a shared interface. Todoist’s official server is hosted, so there’s nothing to install or run yourself:
- Hosted MCP (
ai.todoist.net/mcp) — connects over OAuth and gives an MCP-compatible AI read and write access to your tasks, projects, sections, labels, and comments.
With it connected, an AI client can:
- Read your list — “what’s due today across all my projects?” answered from your live Todoist data.
- Create tasks and projects — turn a rambling note or a pasted email into properly scoped tasks, in the right project, with due dates and labels attached.
- Update and reschedule — rename a task, push a due date, move something to a different project or section, close it out.
- Comment and organize — add context to a task, tidy up labels, or ask for a summary of what’s overdue.
It’s genuinely useful for ad-hoc work: describe what needs doing, get it captured correctly, adjust it on the spot.
How to set up the Todoist MCP server
The hosted server is the quick path — no code, no hosting:
- In your AI client’s connector settings, add the Todoist MCP server (or use the client’s built-in Todoist plugin, where available) pointing at
ai.todoist.net/mcp. - Authorize it against your Todoist account through the OAuth prompt — you’re granting the AI the same access your user has to tasks and projects.
- Confirm the tools appear in the client, then start a chat and ask it to read, add, or reschedule a task.
Because Doist hosts the server itself, there’s no separate deployment to maintain — the setup is entirely on the client side.
Where the Todoist MCP stops
None of this is a knock on MCP — it’s just the shape of the protocol. Four limits show up the moment you want more than a conversation:
- It only works inside a chat you start. Close the window and nothing happens. The AI doesn’t watch Todoist; it waits for you to ask.
- No triggers. A task going overdue, a new email landing, a calendar event ending — none of these can start anything through MCP. There’s no “when this happens, add a Todoist task.”
- It’s one app at a time. The Todoist MCP knows Todoist. Getting a completed task to also update a spreadsheet, notify a teammate on Slack, or log time somewhere else means wiring up a separate MCP server for each, then hoping your client can juggle them in one turn.
- You own the plumbing and the scopes. The OAuth connection, its refresh, and the blast radius of read/write access to your task list are all on you.
So the Todoist MCP is a great way to ask Todoist things and make one-off edits. It is not a way to make Todoist run — to have tasks created or updated on a schedule or in reaction to an event, across the other tools your work touches.
Running Todoist work that doesn’t need a chat open
That “run on its own, across apps” gap is exactly where Carly fits. Carly connects to Todoist natively — no MCP server to authorize each session, no juggling multiple connectors — and to the ~260 other apps it supports, plus anything with a public API through your own key. The difference from MCP is the important part: Carly’s workflows are triggered and scheduled, so Todoist stays current whether or not anyone has a chat window open.
A few things that MCP can’t do but a Carly workflow can:
- When a starred email arrives → turn it into a Todoist task in the right project with a due date, no one copying and pasting.
- Every morning → summarize what’s overdue and due today across your projects and send it to you before you open the app.
- When a task is marked complete → log the time in your tracker and post an update to the team channel it belongs to.
The non-AI steps — the moving, matching, and routing between apps — are free and unlimited, the Zapier-style backbone of the workflow. The AI steps (drafting, summarizing, deciding) start at $35/month. You describe the outcome in plain language and Carly wires up the Todoist connection and everything downstream.
If you just want to interrogate your task list from a chat, Todoist’s official MCP server is the right tool and it’s free to connect. If you want Todoist to actually stay updated — on a trigger, on a schedule, across every app your tasks touch — that’s the job MCP wasn’t built for, and it’s the one Carly was.
FAQ
Does Todoist have an official MCP server?
Yes. Doist hosts it directly at ai.todoist.net/mcp, giving MCP-compatible AI tools read/write access to your tasks, projects, sections, labels, and comments.
Is the Todoist MCP server free? Connecting to it is free; you’re authorizing an AI client against your existing Todoist account through OAuth. You still need whatever Todoist plan your tasks live on.
Can the Todoist MCP trigger automations? No. MCP is request/response inside an AI chat — it has no triggers and nothing runs when the conversation is closed. For event- or schedule-driven Todoist work across apps, you need a workflow tool like Carly rather than an MCP server.
Can I connect Todoist to AI without coding or hosting a server? Yes. You don’t have to touch MCP at all. Carly connects to Todoist for you and lets you build the automation in plain language — describe what you want to happen and it wires up Todoist and the other apps involved, with no server to host and no code to write.
Ready to automate your busywork?
Carly schedules, researches, and briefs you—so you can focus on what matters.
See what people say
"Before Carly, I relied on a Calendly link, but the whole process felt impersonal and not very professional. Carly changed that by handling all the back-and-forth, so I'm no longer stuck in endless email threads trying to line up schedules.
Now Carly reaches out to candidates, shares my real-time availability, lets them pick a slot, then sends a Zoom link and drops it straight into my calendar. She sends reminders to both of us before each call, which has significantly reduced no-shows and last-minute confusion.
On top of scheduling, Carly acts like a full executive assistant, sending me my schedule the night before so I can prepare for each call. It reminds me of the old x.ai assistant, but Carly is noticeably smarter, faster, and better suited to my healthcare recruitment business."
