Calendly Integration for AI Agents

The real problem

Why this is harder than it looks

Calendly's REST API is clean and the documentation is thorough. You can build a working prototype against your own account in an afternoon. The problems arrive when you take this to production for real users.

Calendly uses OAuth 2.0, but you must register your own OAuth app in the Calendly Developer Portal — there is no shared public client you can rely on. That app needs a redirect URI pointing to your infrastructure, and the scopes you request must be explicitly enabled in the app settings before users can authorize. The _default scope covers most scheduling operations, but enterprise features like activity logs require the _{activity_log:read} scope, which is only available on Calendly Enterprise plans. Requesting a scope your Calendly app hasn't enabled causes silent authorization failures that are hard to diagnose. In Workspace or organizational deployments, admins can block third-party app access entirely — and your OAuth flow will fail with no actionable error for the user.

Beyond initial authorization, you need per-user token isolation across a multi-tenant product. Calendly's API surfaces are user-scoped: event types, scheduled events, availability schedules, and routing forms all resolve relative to the authenticated user's organization context. A token from one user cannot be reused for another — and if your routing is wrong, calls succeed silently against the wrong user's data. Tokens refresh on a standard OAuth cycle, but revocation (manual by the user, or triggered by org admin policy) moves the connection to an error state with no automatic recovery.

Scalekit handles OAuth app registration plumbing, token refresh, revocation detection, and per-user isolation. Your agent names a tool and passes parameters. The auth lifecycle is not your problem.

Capabilities

What your agent can do with Calendly

Once connected, your agent has 53 pre-built tools covering the full Calendly API:

• Query and manage scheduled events: list upcoming and past events with time/status filters, retrieve event details, cancel events with optional reason
• Manage event types and availability: create, update, and list event types; read and update availability schedules and rules per event type
• Handle invitees end-to-end: list invitees for events, mark no-shows, create invitees, and manage routing form submissions
• Manage organizations and memberships: send and revoke org invitations, list and remove memberships, retrieve group and group relationship data
• Create scheduling links and shares: generate single-use or limited-use scheduling links; create shareable scheduling pages with custom date ranges and availability overrides
• Subscribe to webhooks: create, list, and delete webhook subscriptions for real-time event notifications

Jump to full tool reference

Setup context

What we're building

This guide connects a scheduling assistant agent to Calendly — helping users query their upcoming meetings, manage event types, and track invitee activity without leaving your product.

Setup

¹ Setup: One SDK, One credential

Install the Scalekit SDK. The only credential your application manages is the Scalekit API key — no Calendly secrets, no user tokens, nothing belonging to your users.

Connected Accounts

² Per-User Auth: Creating connected accounts

Each user gets their own Connected Account — a dedicated auth context scoped to their Calendly organization. The _identifier is any unique string from your system — a UUID, email, or whatever you use internally.

This call is idempotent — safe to call on every session start. Returns the existing account if one already exists.

Authorization Flow

³ The authorization flow

The user authorizes your agent once. Scalekit generates the OAuth URL with correct scopes, PKCE challenge, and redirect handling pre-configured. After approval, you never see the token.

Calling Calendly

⁴ Calling Calendly: What your agent writes

With the connected account active, your agent calls Calendly actions using _{actions.execute_tool()}. Name the tool, pass parameters. Scalekit handles token retrieval and request construction.

Get the current user's profile

Retrieve the authenticated user's Calendly profile — including their organization URI, which you'll need for org-scoped queries like listing memberships or scheduled events.

List upcoming scheduled events

Fetch all active events for a user within a time range. Use _{min_start_time} and _{max_start_time} to scope the window. Filter by _status to separate active from canceled events.

List event types for a user

Retrieve all event types available for a user — useful for presenting scheduling options or updating availability rules. Pass _{active: true} to exclude archived types.

Create a single-use scheduling link

Generate a one-time scheduling link for a specific event type — useful for sending personalized booking links without exposing your main scheduling page. Set _{max_event_count} to 1 for single-use.

Framework wiring

⁵ Wiring into your agent framework

Scalekit integrates directly with LangChain. The agent decides what to call; Scalekit handles auth on every invocation. No token plumbing in your agent logic.

Tool reference

All 53 Calendly tools

Grouped by capability. Your agent calls tools by name — no API wrappers to write.

Connector notes

Calendly-specific behavior

Infrastructure decision

Why not build this yourself

The Calendly OAuth flow is documented. Token storage isn't technically hard. But here's what you're actually signing up for:

That's one connector. Your agent product will eventually need Salesforce, Gmail, Slack, HubSpot, and whatever else your customers ask for. Each has its own OAuth quirks and failure modes.

Scalekit maintains every connector. You maintain none of them.