Google Calendar

Google Calendar

Tools for managing Google Calendar — create, read, update, move, and delete events; search a calendar; list and create calendars; check free/busy availability; resolve the event-color palette; and manage calendar sharing (ACL). Wraps the Google Calendar API v3 (https://www.googleapis.com/calendar/v3/). Authentication is OAuth 2.0 over a single connection — capability is gated by scope and by each calendar's access role, not by token type.

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

When to use this

• An agent needs to schedule, find, reschedule, move, or cancel calendar events.
• An agent needs to check when someone is busy/free across one or more calendars.
• An agent needs to list or create calendars, or read a calendar's default timezone.
• An agent needs to share a calendar with someone or revoke access (ACL management; requires the owner role).

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 google-calendar (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

Each script's inputSchema / outputSchema (Zod) in the script file is the source of truth for its contract.

Disambiguation & refusals

• Resolve before you write. Before creating, moving, or sharing against a calendar or event looked up by name, confirm the target. When resolving a calendar by name via listCalendars, count exact (case-insensitive) summary matches: exactly one → act on it; two or more that tie → stop, list the candidates with their id + accessRole, and ask which one. The same applies to events resolved by listEvents (a person can have several events with the same title) and to ACL rules resolved by listAclRules. Never silently pick the first match.
• Don't fake unsupported operations. This connector does not rename or delete calendars, clear all events from a calendar (calendars.clear), import externally-originated events (events.import), do "this-and-following" recurring edits in one call, or set up triggers/notifications (watch channels). If a user asks for one of these, say it's not supported and stop — don't substitute a different tool (e.g. deleting events one by one to simulate "clear the calendar", or patching the master to fake "this and following") and report success for an action you didn't perform. For a single recurring occurrence, use listEventInstances → updateEvent on the instance id.

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: