Sign in Book a demo
Back to Tools
Productivity & Docs OAuth
Build Your Agent View Calendly Documentation
calendly logo

Calendly MCP Tools for AI Agents

Let an agent find open slots, create single-use booking links, list meetings and invitees, and cancel or mark meetings as no-shows.

Available Tools

12 tools available in this integration

Calendly.CancelScheduledEvent

Cancel a booked Calendly meeting and notify its invitees.

Calendly.CreateSchedulingLink

Create a single-use Calendly booking link for one of your event types.

Calendly.GetScheduledEvent

Get the full detail of one booked Calendly meeting.

Calendly.ListAvailabilitySchedules

List a Calendly user's recurring availability rules and working hours.

Calendly.ListBusyTimes

Find when a Calendly user is already busy over a time window.

Calendly.ListEventAvailableTimes

Find the open booking slots for a Calendly event type over a time window.

Calendly.ListEventInvitees

List who booked a Calendly meeting, with their emails, timezones and status.

Calendly.ListEventTypes

List the meeting types a Calendly user offers, with their booking links.

Calendly.ListOrganizationMembers

List the people in a Calendly organization, with their roles and booking pages.

Calendly.ListScheduledEvents

List a Calendly user's booked meetings, with times, locations and host details.

Calendly.MarkInviteeNoShow

Mark an invitee as having not attended their booked Calendly meeting.

Calendly.WhoAmI

Get the connected Calendly account's profile, timezone and organization.

Working directly against the raw API? 51 more tools in the Calendly API server →

Why agent-optimized tools matter

Built for intent, not API schemas

Ask the agent to "find an open slot for a 30-minute intro next week and create a single-use booking link." Arcade picks the right Calendly actions without guessing event type or user IDs.

Up to 100x fewer tokens

Calendly reads return focused event, invitee, availability, and organization details, so the agent can choose a slot or review a meeting without loading unrelated scheduling records into the model.

Complete the workflow end to end

Check availability, find an event type, create a booking link, inspect the booked meeting, and cancel it when plans change through one toolkit designed around the complete scheduling task.

Make actions predictable and controlled

Arcade tools return structured results and useful errors across users and runs. Teams can apply scope restrictions, redaction, and approval policies so agents follow the same controls every time.

Securing Calendly

The more capabilities agents get, the more useful they are. However, more capabilities bring more risks of undesired effects such as data loss and exfiltration.

This is why Arcade provides you with contextual rules that dictate how and when a tool is allowed to run. Arcade’s contextual access lets you govern tool visibility and behavior at every stage of execution and control who can see a tool, what inputs are allowed, and what comes back.

Learn about Contextual Access Policies

For Calendly, you can implement some of these policies:

Access when tools are listed for a user
  • Hide Calendly.CancelScheduledEvent from agents unless the roles your IDP marks as scheduling administrators are active, so regular agents cannot cancel meetings and notify invitees.
  • Restrict Calendly.CreateSchedulingLink to agents operating under your recruiting or sales roles, so unapproved agents cannot create booking links that expose your calendar.
  • Deny Calendly.MarkInviteeNoShow to everyone outside the roles your IDP marks as meeting hosts or coordinators, so an agent cannot wrongly record that someone missed a meeting.
Pre-execution before each tool call
  • Require human approval before Calendly.CancelScheduledEvent runs, so an agent cannot cancel a meeting and notify invitees without review.
  • Block Calendly.CreateSchedulingLink when the requested event type is not on your approved list, so an agent cannot publish booking links for private or unapproved meetings.
  • Require human approval before Calendly.MarkInviteeNoShow runs, so an agent cannot create an inaccurate attendance record that could affect follow-up or reporting.
Post-execution after the tool returns
  • Redact email addresses, phone numbers, and timezone details from Calendly.ListEventInvitees results before they reach the model, so an agent receives attendance status without unnecessary invitee contact data.
  • Strip personal email addresses and other private profile fields from Calendly.ListOrganizationMembers results, so the model sees member roles and booking pages without exposing direct contact details.
  • Redact the connected account's email address and organization identifiers from Calendly.WhoAmI results before the model sees them, so account context does not become prompt-visible personal data.

How to use Calendly with your agent

Connect your Calendly account, add the MCP server to your client, and start scheduling from natural-language prompts. Each user authorizes their own account.

Your questions, answered

A Calendly MCP server exposes Calendly scheduling capabilities as structured tools that an AI agent can call through the Model Context Protocol. After a user authorizes their Calendly account, the agent can check availability, inspect bookings, create scheduling links, and manage invitees within the granted permissions.

Calendly provides an API, but this integration does not depend on a separate Calendly-hosted MCP server. Arcade adds user-level OAuth, a consistent MCP and tool interface, approval workflows, redaction, and scope controls around Calendly actions.

Arcade agents can list event types, recurring availability, busy times, open booking slots, scheduled meetings, invitees, organization members, and account details. They can also create single-use scheduling links, cancel meetings, and mark invitees as no-shows.

Arcade requests the Calendly OAuth permissions required by the actions you enable. Read-only workflows need access to the relevant Calendly account, event, availability, and organization data; creating links, canceling meetings, or marking no-shows requires the corresponding write permissions. Grant the narrowest permissions that support your workflow.

Yes. Each user authorizes their own Calendly account through OAuth. Actions run under that user's authorization, so the agent can access only the account and permissions that user approved.

Yes. Contextual Access policies can require human approval before consequential Calendly actions such as canceling a booked meeting or marking an invitee as a no-show. The call proceeds only after the policy's conditions have been satisfied, and policies can also redact response fields or hide actions from an agent.

Arcade proxies Calendly API calls and does not persist your Calendly content as part of normal tool execution. OAuth credentials are brokered and stored encrypted at rest, and the model never receives them.

Any framework or client that can connect to Arcade's MCP gateway or tool APIs works, including LangChain, OpenAI Agents, CrewAI, Claude Desktop, Claude Code, Cursor, Visual Studio Code, Microsoft Copilot Studio, and GitHub Copilot.

Arcade refreshes access while the user's Calendly authorization remains valid. If access is revoked, rotated, or can no longer be refreshed, Calendly actions stop until the user reconnects their account.

Calendly's API rate limits and quotas still apply to actions performed through Arcade. Design workflows to avoid unnecessary repeated availability, event, and invitee queries, and handle rate-limit responses with normal retry and backoff logic.

Ready to actually ship your agent?

Connect your agent to Calendly with managed OAuth, agent-optimized tools and approval controls for consequential actions.

Build Your Agent Read the Calendly Quickstart