Microsoft Todo

Microsoft Todo

Agent-callable tools for Microsoft To Do against the Microsoft Graph v1.0 To Do API (https://graph.microsoft.com/v1.0/me/todo/...): list/get/create/update/delete task lists, list/get/create/update/delete tasks, find a task by title, mark a task complete, and manage a task's checklist items (steps). 16 scripts, all against a single user's task lists over one OAuth connection.

Independent, unofficial connector for Microsoft Todo. Not affiliated with, endorsed by, or sponsored by Microsoft Todo. "Microsoft Todo" is a trademark of its owner, used only to identify the service this connector works with.

When to use this

• An agent needs to capture or find a task — create a task (optionally in the default list), find one by title, or list/filter tasks in a list.
• An agent needs to organize tasks or lists — create/rename/delete task lists, update a task's due date, importance, or status, or delete a task.
• An agent needs to complete or reopen work — mark a task done with completeTask, or reopen it via updateTask(status: "notStarted").
• An agent needs to break a task into steps — list, add, update, or delete a task's checklist items (subtasks).

Setup

This is an agentskills.io skill.

If the connector has not been installed as a skill yet, install it first with npx skills add zapier/connectors --skill microsoft-todo (or your harness's own skill-install mechanism), then continue here. Installing the skill copies these files, not dependencies. Before running the CLI, a local MCP server, or zapier-sdk auth commands, run npm install --omit=dev here once. Importing the published package as a dependency in your own project instead? That npm install already resolves everything — see references/use-as-sdk.md.

Want the actual repo source instead — to browse references/, run this connector's tests, or hack on it? See README.md for a scoped git clone.

The connector runs on Node.js 22.18+. Pick the reference that matches how you're running it, and load it before doing anything else:

Scripts

All scripts use the single connection microsoft-todo. listId is optional on createTask/listTasks/findTask (omit to target your default list); every other task/checklist script requires an explicit listId from listLists.

Disambiguation & refusals

Disambiguation before acting on a looked-up task. Before updating, completing, or deleting a task resolved by title (via findTask or listTasks(filter)), count the matches — task titles aren't unique in Microsoft To Do:

• Exactly one match — act on it. Don't over-ask; a single unambiguous match is the answer.
• Two or more that tie — stop. List the tied candidates with a distinguishing field (id, dueDateTime, or createdDateTime) and ask the user which one they mean. Don't pick arbitrarily and don't act on all of them.

Unsupported operations — say so and stop; don't fake it with another tool. This catalog deliberately does not:

• Author recurring/repeating tasks. createTask/updateTask have no recurrence input. If asked to create a task that repeats, create the one-time task and say recurrence isn't supported — don't invent a workaround that silently drops the repeat.
• Move a task between lists as a single operation. There's no moveTask tool. To relocate a task, create it in the target list and delete the original — and say so, since the task gets a new id (a task's id changes whenever it moves between lists; don't claim the original id was relocated in place).
• Show a task's linked source item (e.g. the email it was created from). linkedResources aren't exposed by any tool — only checklistItems (steps) are.

If asked for any of these, tell the user it's unsupported (or, for a move, explain the recreate-and-delete workaround) and stop — don't reach for an unrelated tool to approximate it.

Auth

Every shape passes auth as one connection selector, not the secret — a [<resolver>:]<value> string. Every connector accepts zapier:<connection-id> (Zapier-managed auth — routes through Zapier's auth, retries, and governance layer); some also accept one or more direct-token resolvers (naming and count vary per connector) — check this connector's own resolvers rather than assuming. The <resolver>: prefix is optional; a bare value goes to the first resolver that claims it — a UUID-shaped bare value always claims zapier:. Each script declares the connections it needs and the resolvers each accepts. The exact syntax for passing a connection (and how to see this connector's resolver list) differs by shape — see the reference you loaded above.

Checking what's already configured first? Don't dump environment values to do it — env or env | grep <name> prints the value along with the name, leaking a live credential into the transcript if one is set. Check names only (env | cut -d= -f1 | grep -i <name>) or test a known name directly ([ -n "$VAR_NAME" ]).

No connection yet? Pick one — and follow the reference's own flow to obtain it; never just ask the user for a connection id or token as if they already have one memorized:

Output format

Every script returns a { data, meta } envelope:

• data — the script's result (the shape its outputSchema declares; see the reference you loaded above for how to inspect a script's exact schema in your shape).
• meta.outputDataValidation — what validating data did:
  • { skipped: false, droppedPaths: null } — validated, nothing removed.
  • { skipped: false, droppedPaths: [...], instruction } — validated, but those paths were stripped from data: fields the script returned from the API that the outputSchema doesn't declare. If you need them, re-run with output validation skipped.
  • { skipped: true } — validation was bypassed; data is the raw, unchecked script output.

Reading dropped fields / skipOutputDataValidation. To receive the raw, unvalidated result, opt out of output validation (the exact syntax differs by shape — see the reference you loaded above). Input validation is never skipped.

Trimming the result / filterOutputData. To shrink a large result down to the fields you need, pass a jq expression that post-processes data (again, exact syntax per shape). The jq runs against data only, NOT the { data, meta } envelope, so write it rooted at data (run the script's --help — or your shape's equivalent — to see its output schema). The transformed value replaces data, meta is preserved, and the result is NOT re-validated against the output schema.

References

Load the matching reference file before working in that area: