Microsoft Outlook

Microsoft Outlook

Tools for a single user's Outlook mailbox against the Microsoft Graph API v1.0 (https://graph.microsoft.com/v1.0/): read and search mail, compose/send/reply/forward, organize messages (read state, flag, importance, categories, move, copy, delete), browse mail folders and attachments, manage calendar events, and manage personal contacts. 30 scripts across profile, mail, folders, categories, calendar, and contacts. All calls authorize with one OAuth bearer token.

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

When to use this

• An agent needs to read or search mail — list/search messages (by folder, KQL, or OData filter), read a full message, list and download attachments.
• An agent needs to send or reply — compose-and-send, create a draft and send it later, reply / reply-all, or forward.
• An agent needs to organize mail — mark read/unread, flag, set importance, categorize, move, copy, or delete a message; browse and create mail folders.
• An agent needs to work with the calendar or contacts — list calendars, list events or a date-range view, create / update / delete events, and create / read / update / delete personal contacts.

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-outlook (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-outlook. Mail and calendar scripts accept an optional mailbox input to act on a shared mailbox; the six event scripts accept an optional calendarId (resolve it via listCalendars).

Disambiguation & refusals

Disambiguation before a write. Before acting on a contact, event, or message you looked up by name/subject (e.g. update a contact found via listContacts, or reply to an event found via listEvents), count the exact case-insensitive matches on the name/subject:

• 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 (a contact's emailAddresses/companyName, an event's start/organizer, a message's from/receivedDateTime) and ask the user which one they mean. Don't pick arbitrarily and don't write to all of them.

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

• Watch for new mail or events (triggers). There is no "notify me when an email arrives" or polling tool; the connector is request/response only. Don't simulate it with repeated listMessages calls and claim it's a subscription.
• Send attachments larger than 3 MB. Only inline attachments under 3 MB are supported; large-file upload sessions are not. Don't claim a large file was sent.
• Access group / shared calendars or distribution lists. Group calendars and directory groups aren't exposed. (Shared mailboxes are, via the mailbox input.)
• Permanently delete mail (deleteMessage is a reversible move to Deleted Items) or manage mailbox rules, auto-replies, or focused-inbox settings.

If asked for any of these, tell the user it's unsupported 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: