Aircall connector for AI agents

Tools your calling agent reaches for on Aircall, scoped per user.

CALL ANY TOOL

78 tools for calling in Aircall: search calls, read AI summaries, transcripts, and sentiment, manage contacts, tags, and numbers, run Outbound Campaigns and Power Dialer lists, and send SMS and WhatsApp messages.

aircall_ai_voice_agent_call_trigger

Trigger ai voice agent call

Ask an Aircall Outbound AI Voice Agent to call a contact, for example for an appointment reminder or a follow-up. The request is queued and placed when a calling slot is free. Returns id, idempotency_key, status (PENDING) and virtual_agent_id (HTTP 202). Use aircall_ai_voice_agent_call_trigger for AI-placed calls. Use aircall_user_call_start for a call placed by a human user. The agent must be configured in the Aircall Dashboard with a phone number and a first message.

Parameters

Name

Type

Required

Description

agent_id

string

Required

ID of the Outbound Voice Agent, from the Outbound Call Workflow tab of the agent's configuration page. Example: agent-abc123

contact_phone

string

Required

Phone number to call, with country code. A leading + is optional. Example: +15551234567

idempotency_key

string

Required

Unique key for this call request; sending the same key twice won't create a second call. Use a new key for every retry. Example: appt-reminder-2026-03-15-cust-12345

context

object

Optional

Values for the {{variable}} placeholders in the agent's first message, voicemail message and guidelines. Every variable in the first message and voicemail message must be present. Add a timezone key (IANA, such as America/New_York) when a value is a UTC datetime. Example: {"first_name": "Jane", "appointment_date": "March 20th at 2:00 PM"}

expiration_seconds

integer

Optional

How long, in seconds, to keep trying to place the call if the concurrency limit is reached: 60 to 86400. Default: 3600. Default: `3600`.

aircall_analytics_export_create

Create analytics export

Start an asynchronous Analytics report export (CSV), such as the call history or user status history for a date range. Requires the Analytics+ entitlement. Returns exportID, createdAt and status (PENDING). Use aircall_analytics_export_create to request a report, then poll aircall_analytics_export_get with the exportID until it is COMPLETED.

Parameters

Name

Type

Required

Description

filter

object

Required

Report filters. Required: timezone (IANA, such as Europe/Paris) and dateFilter with exactly one of relative (LAST_MONTH, LAST_WEEK, THIS_MONTH, THIS_WEEK, TODAY or YESTERDAY) or absoluteRange (fromDate and toDate as YYYY-MM-DD). Optional array filters include userIDs, teamIDs, lineIDs, tagIDs, callIDs and customerNumbers (always arrays, even for one value), plus callTypes, duration, hours and voicemail or AI flags. Example: {"timezone": "Europe/Paris", "dateFilter": {"absoluteRange": {"fromDate": "2026-05-01", "toDate": "2026-05-15"}}, "teamIDs": [4242]}

report_name

string

Required

Report to export. CALLS_HISTORY is the raw call log; USER_STATUS_HISTORY is raw status changes; USER_ACTIVITY_* reports aggregate per user. One of: `CALLS_HISTORY`, `USER_STATUS_HISTORY`, `USER_ACTIVITY_AVAILABILITY_BREAKDOWN`, `USER_ACTIVITY_AVERAGE_AFTER_CALL_WORK_TIME_PER_USER`, `USER_ACTIVITY_AVERAGE_INBOUND_IN_CALL_TIME_PER_USER`, `USER_ACTIVITY_AVERAGE_OUTBOUND_IN_CALL_TIME_PER_USER`, `USER_ACTIVITY_CALL_VOLUME_AND_TIME`, `USER_ACTIVITY_CALLS_HANDLED`, `USER_ACTIVITY_PERCENTAGE_OF_TIME_IN_EACH_STATUS`, `USER_ACTIVITY_RINGING_ATTEMPTS_PER_USER`, `USER_ACTIVITY_WORK_TIME_AND_AVAILABILITY`, `USER_ACTIVITY_RINGING_ATTEMPTS`.

export_options

object

Optional

File options: format (only CSV is supported) and exportName, a name echoed back on retrieve. Example: {"format": "CSV", "exportName": "calls-history-may-2026"}

options

object

Optional

Report options: dateBreakdown (HOURLY, DAILY, WEEKLY or MONTHLY) for USER_ACTIVITY_* reports, and SLA settings slaTimeToAnswerInSeconds and slaIncludedCallUnansweredReasons for call-based metrics. Example: {"dateBreakdown": "DAILY", "slaTimeToAnswerInSeconds": 20}

aircall_analytics_export_get

Get analytics export

aircall_call_evaluations_get

Get call evaluations

aircall_call_predicted_csat_get

Get call predicted csat

aircall_call_recording_pause

Pause call recording

aircall_call_tags_add

Add call tags

aircall_call_topics_get

Get call topics

aircall_call_transfer

Call transfer

aircall_calls_list

List calls

aircall_calls_search

Search calls

aircall_campaign_contact_remove

Remove campaign contact

aircall_campaign_contacts_list

List campaign contacts

aircall_campaign_pause

Pause campaign

aircall_campaign_stats_get

Get campaign stats

aircall_contact_create

Create contact

aircall_contact_delete

Delete contact

aircall_contact_email_add

Add contact email

aircall_contact_email_update

Update contact email

aircall_contact_update

Update contact

aircall_contacts_list

List contacts

aircall_dialer_campaign_delete

Delete dialer campaign

aircall_dialer_campaign_get

Get dialer campaign

aircall_group_message_send

Send group message

aircall_number_registration_status_get

Get number registration status

aircall_sms_templates_list

List sms templates

aircall_teams_list

List teams

aircall_tracker_get

Get tracker

aircall_user_call_start

Start user call

aircall_users_availabilities_list

List users availabilities

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

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

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

// Aircall tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aircall"], toolNames: [
    "aircall_calls_search",
    "aircall_call_summary_get",
    "aircall_call_comment_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Summarize my last call with Contoso and add a comment" }] });

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aircall"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Summarize my last call with Contoso and add a comment" }],
  tools,
});

// Execute the tool call with the user's vaulted Aircall OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aircall"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Summarize my last call with Contoso and add a comment" }],
  tools,
});

// Tool call runs with the user's vaulted Aircall OAuth token
await sk.tools.executeTool(msg.content, "user_123");

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

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

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["aircall"] }, pageSize: 100,
});

const agent = new Agent({
  name: "calling_agent",
  model: "gemini-2.5-pro",
  instruction: "Aircall tools scoped to this user",
  tools,
});

await agent.run("Summarize my last call with Contoso and add a comment");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Aircall tool. Click to copy, paste into your agent, done.

Calls and insights

Copy the prompt

Copied

Summarize my last call with Contoso.

Copy the prompt

Copied

List the action items from yesterday's call with Fabrikam.

Copy the prompt

Copied

List inbound calls from today.

Contacts and tags

Copy the prompt

Copied

Create a shared contact for Dana Kim with her mobile number.

Copy the prompt

Copied

Tag the Contoso call as renewal.

Copy the prompt

Copied

Search contacts by the number +1 415 555 0134.

Outreach

Copy the prompt

Copied

Add these 40 contacts to the Q4 renewal campaign.

Copy the prompt

Copied

Pause the Q4 renewal campaign.

Copy the prompt

Copied

Send an SMS from our support line confirming tomorrow's appointment.

SEE HOW AUTH WORKS

Each user signs in to Aircall once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Aircall

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

Store

Their

Aircall

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

Resolve

When your agent calls a

Aircall

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

Audit

Every

Aircall

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 communication and support connectors.

GTM and RevOps Teams

Sales call prep agent

Reads tomorrow's calls from Google Calendar, mines past Granola notes and Attio history for context, and delivers each rep a prep brief in Slack, scoped to the calls that rep actually owns.

Support and Ops Teams

Support triage agent

Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.

GTM and RevOps Teams

Deal intelligence agent

Pulls recent Gong calls, scores deal risk with an LLM, cross-references the record in Attio, and DMs each owner their at-risk deals in Slack. Every read is scoped to that rep's own access.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Aircall token looks fine in a demo. In production every call note and SMS looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Aircall today. Ten connectors 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 Aircall as the user or through a shared service account?

As the user. Each user signs in to Aircall once, and Scalekit stores and refreshes their tokens. Every call comment, contact change, and message in your audit trail is attributed to that user, not a shared service account.

Where is the Aircall OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Aircall?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example call search and summaries without aircall_message_send, or without aircall_contact_delete, which deletes a shared contact and cannot be undone. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Aircall access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

What do the Aircall AI call tools need?

aircall_call_summary_get, aircall_call_topics_get, aircall_call_sentiments_get, and the other AI insight tools require the Aircall AI Assist or AI Assist Pro package. aircall_calls_search covers the company's calls from the last six months.