Cal connector for AI agents

CALL ANY TOOL

Check availability, create and reschedule bookings, list event types, and cancel meetings, each call scoped to the authenticated user's own calendar access.

cal_availability_get

Get availability

Return open time slots for a user or event type across a date range, respecting buffers and booking limits.

Parameters

Name

Type

Required

Description

event_type_id

integer

Optional

Event type to check availability for

date_from

string

Required

Start of the date range in ISO 8601

date_to

string

Required

End of the date range in ISO 8601

cal_bookings_list

List bookings

cal_booking_create

Create booking

cal_booking_reschedule

Reschedule booking

cal_booking_cancel

Cancel booking

cal_event_types_list

List event types

Build your Agent

The same per-user auth pattern wires into every agent framework.

import { ScalekitClient } from "@scalekit-sdk/node";
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["calmcp"], toolNames: ["cal_availability_get", "cal_bookings_list", "cal_booking_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm: new ChatOpenAI({ model: "gpt-4o" }), tools });
await agent.invoke({ messages: [{ role: "user", content: "Book a 30-minute intro call next week" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const openai = new OpenAI();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["calmcp"], toolNames: ["cal_availability_get", "cal_bookings_list", "cal_booking_create"] },
  pageSize: 100,
});

const res = await openai.responses.create({
  model: "gpt-4o",
  input: "Find an open slot with Priya and book it",
  tools,
});

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const anthropic = new Anthropic();
const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["calmcp"], toolNames: ["cal_availability_get", "cal_bookings_list", "cal_booking_create"] },
  pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-4-6",
  max_tokens: 1024,
  tools,
  messages: [{ role: "user", content: "Reschedule my Thursday call to next Monday" }],
});

import { LlmAgent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(process.env.SCALEKIT_ENV_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["calmcp"], toolNames: ["cal_availability_get", "cal_bookings_list", "cal_booking_create"] },
  pageSize: 100,
});

const agent = new LlmAgent({ name: "cal_agent", model: "gemini-2.0-flash", tools });
await agent.run("List my upcoming bookings this week");

Try these prompts

Paste any prompt into your agent to start managing Cal.com bookings.

Book & schedule

Copy the prompt

Copied

Find me a 30-minute slot with Priya next week and book it.

Copy the prompt

Copied

Book a discovery call with acme@example.com on Thursday afternoon.

Copy the prompt

Copied

Check my open slots for the intro-call event type next week.

Manage bookings

Copy the prompt

Copied

Reschedule my Thursday 3pm call to next Monday morning.

Copy the prompt

Copied

Cancel the demo booking with globex@example.com and let them know.

Copy the prompt

Copied

Move all my Friday meetings back by 30 minutes.

Report & recall

Copy the prompt

Copied

List all my upcoming bookings this week.

Copy the prompt

Copied

Which event types do I currently offer?

Copy the prompt

Copied

How many meetings did I have last month?

SEE HOW AUTH WORKS

The user authorises Cal.com once. Every later agent call uses their token with calendar scope enforced.

1

Authorize

Your user connects

Cal MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

2

Store

Their

Cal MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

3

Resolve

When your agent calls a

Cal MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

4

Audit

Every

Cal MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other calendar connectors.

OPS

Email-to-calendar scheduling agent

Parse scheduling intent from Gmail threads and create Google Calendar events with the right attendees and timezone.

Gmail

Google Calendar

View agent

SALES

Sales call prep agent

Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.

Granola

Attio

View agent

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought. Calendar data needs real per-user attribution.

01.

Shared tokens break per-user analytics

A shared Cal.com token looks fine in a demo. In production every booking and cancel logs as one service account, so you lose track of whose calendar was touched. Scalekit resolves the real user's credential per call.

// shared token
book → scheduling_bot

// scalekit
book → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Cal today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Cal.com as the user or as a shared key?

As the user. Scalekit resolves the authenticated user's own Cal.com credential at request time, so every booking, reschedule, and cancel is attributed to them in Cal.com rather than a shared scheduling bot.

Where is the Cal.com token stored?

In an AES-256 encrypted vault, namespaced per tenant. Tokens are fetched only at the moment of a tool call, refreshed automatically before expiry, and revocable from a single dashboard, never exposed to the model or the prompt.

Can I limit what the agent is allowed to do in Cal.com?

Yes. Pass a toolNames filter to listScopedTools to expose only the actions you want, for example read-only availability and booking lists without create or cancel. Scalekit also runs a scope check before each API call.

What happens when a user revokes Cal.com access?

The credential is invalidated at the next tool call, which fails closed rather than falling back to a shared token. Other users are unaffected, and the revocation is recorded in the audit trail.

Can the agent book meetings across time zones and event types?

Yes. Availability is resolved against the user's own working hours, buffers, and booking limits, and Cal.com handles timezone detection for each attendee. You choose which event types the agent can book by scoping the toolNames and event type IDs it receives.

Cal MCP

Tools your scheduling agent reaches for on Cal.com, scoped per user.