Connect AI agents to Granola

Scalekit connector

The Granola connector lets your AI agent act in each user's Granola account. Each user connects their own Granola access token once, and Scalekit sends it with every call, so your agent never handles credentials. Your agent calls the Granola API as the user through Scalekit's API proxy.

Tools: 9
What they doRead · write · destructive: 6 · 2 · 16 read2 write1 destructive
Users sign in with: Access token

What you can do

Read meeting notes: list and fetch notes with titles, attendees, calendar details, and AI-generated summaries
Get transcripts: pull the full transcript of any meeting, paging through long conversations
Browse folders: list workspace folders and use them to filter notes
Manage webhooks: create, update, list, and delete endpoints that receive events when notes are generated or edited
Review audit events: list workspace audit events filtered by action and date range

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Granola connection
In AgentKit > Connections, create a Granola connection. The name you give it is the connection_name your code passes. See Configure connections.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'granola'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Granola:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'granola_audit_events_list',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "granola"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Granola:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="granola_audit_events_list",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user opens the link once and enters their Granola credentials there. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

granola_audit_events_listList paginated audit events for the Granola workspace, optionally filtered by action (exact match or prefix) and a date range.Read-only
List Audit Events
List paginated audit events for the Granola workspace, optionally filtered by action (exact match or prefix) and a date range.
Inputs
actionstring
Filter by an exact action name or prefix, e.g. 'note.' to match all note-related actions.
cursorstring
Pagination cursor from the previous response to fetch the next page of results.
occurred_afterstring
Only return events that occurred on or after this date. ISO 8601 format (e.g., 2024-01-01 or 2024-01-01T00:00:00Z).
occurred_beforestring
Only return events that occurred before this date. ISO 8601 format (e.g., 2024-12-31 or 2024-12-31T23:59:59Z).
page_sizeinteger
Number of audit events to return per page (1-30). Defaults to 10.
granola_folders_listList all folders accessible in the Granola workspace, with pagination.Read-only
List Folders
List all folders accessible in the Granola workspace, with pagination. Use folder IDs from this tool to filter notes or scope webhook endpoints.
Inputs
cursorstring
Pagination cursor from the previous response to fetch the next page of results.
page_sizeinteger
Number of folders to return per page (1-30). Defaults to 10.
granola_note_getRetrieve a single Granola meeting note by its ID.Read-only
Get Note
Retrieve a single Granola meeting note by its ID. Returns the full note including title, owner, calendar event details, attendees, folder memberships, and AI-generated summary. Optionally include the full transcript with speaker labels and timestamps.
Inputs
note_idstringrequired
The unique identifier of the note to retrieve. Format: not_XXXXXXXXXXXXXX.
includestring
Pass 'transcript' to include the full meeting transcript with speaker source and timestamps.one of transcript
granola_note_transcript_getRetrieve the full meeting transcript for a Granola note, paginated with a cursor.Read-only
Get Note Transcript
Retrieve the full meeting transcript for a Granola note, paginated with a cursor. Use this instead of granola_note_get's include=transcript option when a transcript is too large to inline, or when you need to page through a long transcript explicitly.
Inputs
note_idstringrequired
The unique identifier of the note whose transcript should be retrieved. Format: not_XXXXXXXXXXXXXX.
cursorstring
Pagination cursor from a previous response to fetch the next page of transcript entries.
page_sizeinteger
Number of transcript entries to return per page (1-100). Defaults to 50.
granola_notes_listList all accessible meeting notes in the Granola workspace with pagination and date filtering.Read-only
List Notes
List all accessible meeting notes in the Granola workspace with pagination and date filtering. Returns note IDs, titles, owners, calendar event details, attendees, folder memberships, and AI-generated summaries. Only notes shared in workspace-wide folders are accessible.
Inputs
created_afterstring
Filter notes created on or after this date. ISO 8601 format (e.g., 2024-01-01 or 2024-01-01T00:00:00Z).
created_beforestring
Filter notes created before this date. ISO 8601 format (e.g., 2024-12-31 or 2024-12-31T23:59:59Z).
cursorstring
Pagination cursor from the previous response to fetch the next page of results.
page_sizeinteger
Number of notes to return per page (1–30). Defaults to 10.
updated_afterstring
Filter notes updated after this date. ISO 8601 format (e.g., 2024-06-01 or 2024-06-01T00:00:00Z).
granola_webhook_endpoints_listList all webhook endpoints configured for the Granola workspace, including their URL, scopes, subscribed event types, and enabled state.Read-only
List Webhook Endpoints
List all webhook endpoints configured for the Granola workspace, including their URL, scopes, subscribed event types, and enabled state.
Inputs
This tool takes no inputs.
granola_webhook_endpoint_createRegister a new HTTPS webhook endpoint to receive Granola event deliveries (e.g.Write
Create Webhook Endpoint
Register a new HTTPS webhook endpoint to receive Granola event deliveries (e.g. note generated or edited). Returns a signing_secret used to verify delivered payloads.
Inputs
scopesarrayrequired
Which note visibility scopes this endpoint should receive events for. At least one of: personal, public, workspace.
urlstringrequired
The publicly reachable HTTPS URL that Granola should deliver events to.
eventsarray
Which event types to subscribe to. If omitted, defaults to all event types. At least one of: note.access_granted, note.edited, note.generated.
folder_idsarray
Restrict delivered events to notes in these folders only (up to 100 folder IDs). If omitted, events are not filtered by folder.
granola_webhook_endpoint_updateUpdate an existing Granola webhook endpoint's URL, scopes, subscribed events, folder filter, or enabled state.Write
Update Webhook Endpoint
Update an existing Granola webhook endpoint's URL, scopes, subscribed events, folder filter, or enabled state. Only the fields provided are changed.
- Idempotent
Inputs
webhook_endpoint_idstringrequired
The unique identifier of the webhook endpoint to update. Format: whe_XXXXXXXXXXXXXX.
enabledboolean
Enable or disable this webhook endpoint without deleting it.
eventsarray
New set of event types to subscribe to. At least one of: note.access_granted, note.edited, note.generated.
folder_idsarray
New list of folder IDs to restrict delivered events to (up to 100). Pass an empty array to remove the folder filter entirely.
scopesarray
New set of note visibility scopes this endpoint should receive events for. At least one of: personal, public, workspace.
urlstring
New publicly reachable HTTPS URL for Granola to deliver events to.
granola_webhook_endpoint_deletePermanently remove a Granola webhook endpoint.Destructive
Delete Webhook Endpoint
Permanently remove a Granola webhook endpoint. Event deliveries to it stop immediately.
- Idempotent
Inputs
webhook_endpoint_idstringrequired
The unique identifier of the webhook endpoint to delete. Format: whe_XXXXXXXXXXXXXX.

What you can do

Setup

Install the SDK

Set your credentials

Create the Granola connection

Authorize a user and make your first call

Tools

Call it

Returns

List Audit Events

Inputs

List Folders

Inputs

Get Note

Inputs

Get Note Transcript

Inputs

List Notes

Inputs

List Webhook Endpoints

Inputs

Create Webhook Endpoint

Inputs

Update Webhook Endpoint

Inputs

Delete Webhook Endpoint

Inputs

Related: other AI connectors