Grain connector | Meeting recordings for AI agents

Tools your meeting intelligence agent reaches for on Grain, scoped per user.

CALL ANY TOOL

Meeting recordings on Grain's REST API: search recordings, pull transcripts and highlights, upload media, and manage workspace webhooks.

grain_hook_create

Create hook

Register a webhook (hook) that Grain calls with an HTTP POST whenever the given event type occurs: new/updated/deleted recordings, highlights, or stories, or upload processing status changes.

Parameters

Name

Type

Required

Description

hook_type

string

Required

The event type this webhook subscribes to.

hook_url

string

Required

HTTPS URL that Grain will POST event payloads to.

grain_hook_delete

Delete hook

grain_hooks_list

List hooks

grain_meeting_types_list

List meeting types

grain_recording_download

Download recording

grain_recording_get

Get recording

grain_recording_share_team

Recording share team

grain_recording_share_user

Recording share user

grain_recording_tag_add

Add recording tag

grain_recording_tag_remove

Remove recording tag

grain_recording_transcript_get

Get recording transcript

grain_recording_transcript_text_get

Get recording transcript text

grain_recording_unshare_team

Recording unshare team

grain_recording_unshare_user

Recording unshare user

grain_recording_update

Update recording

grain_recording_upload_url_create

Create recording upload url

grain_recordings_list

List recordings

List meeting recordings in the Grain workspace (or, with a Personal Access Token, the caller's own recordings). Supports filtering by date range, title search, team, meeting type, attendance, and participant scope, plus optional inclusion of highlights, participants, AI summary/action items, and more. Returns a page of recordings and a cursor for the next page.

Parameters

Name

Type

Required

Description

after_datetime

string

Optional

Only return recordings whose start_datetime is after this ISO8601 timestamp (inclusive).

attendance

string

Optional

Personal Access Token only. 'hosted' returns only recordings the caller hosted; 'attended' returns only recordings the caller attended.

before_datetime

string

Optional

Only return recordings whose start_datetime is before this ISO8601 timestamp (exclusive).

cursor

string

Optional

Pagination cursor from a previous response's cursor field, used to fetch the next page.

include_ai_action_items

boolean

Optional

Include AI-detected action items in the response.

include_ai_summary

boolean

Optional

Include the AI-generated meeting summary in the response.

include_calendar_event

boolean

Optional

Include the linked calendar event details in the response.

include_highlights

boolean

Optional

Include each recording's highlights in the response.

include_hubspot

boolean

Optional

Include linked HubSpot company and deal ids in the response.

include_participants

boolean

Optional

Include each recording's participant list in the response.

include_private_notes

boolean

Optional

Personal Access Token only. Include the caller's private notes on each recording.

include_screenshares

boolean

Optional

Include screenshare timing segments in the response.

meeting_type_id

string

Optional

Only return recordings matching this meeting type id (UUID). Use grain_meeting_types_list to discover meeting type ids.

participant_scope

string

Optional

'internal' returns only internal/team meetings; 'external' returns only external/customer meetings.

team_id

string

Optional

Only return recordings belonging to this team id (UUID). Use grain_teams_list to discover team ids.

title_search

string

Optional

Return recordings whose title matches this search string.

grain_teams_list

List teams

grain_users_list

List users

Build your Agent

Drop the toolkit in, point it at the user, and your meeting intelligence agent can use Grain from the first run.

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);

// Grain tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grain"], toolNames: [
    "grain_hook_create",
    "grain_hook_delete",
    "grain_hooks_list"
  ] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "What did Acme say about pricing on last week's call?" }] });

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);

// Grain tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grain"], toolNames: [
    "grain_hook_create",
    "grain_hook_delete",
    "grain_hooks_list"
  ] },
  pageSize: 100,
});

const openai = new OpenAI();
const res = await openai.responses.create({
  model: "gpt-5",
  tools: tools.map((t) => t.openai),
  input: "What did Acme say about pricing on last week's call?",
});

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);

// Grain tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grain"], toolNames: [
    "grain_hook_create",
    "grain_hook_delete",
    "grain_hooks_list"
  ] },
  pageSize: 100,
});

const anthropic = new Anthropic();
const msg = await anthropic.messages.create({
  model: "claude-opus-4-6",
  max_tokens: 1024,
  tools: tools.map((t) => t.anthropic),
  messages: [{ role: "user", content: "What did Acme say about pricing on last week's call?" }],
});

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);

// Grain tools, scoped to the signed-in user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["grain"], toolNames: [
    "grain_hook_create",
    "grain_hook_delete",
    "grain_hooks_list"
  ] },
  pageSize: 100,
});

const agent = new Agent({
  name: "grain_agent",
  model: "gemini-2.5-pro",
  instruction: "Act as the meeting intelligence agent for the signed-in user.",
  tools,
});
await agent.run("What did Acme say about pricing on last week's call?");

Try these prompts

Paste any prompt into your agent to start using Grain.

Call research

Copy the prompt

Copied

What did Acme say about pricing on last week's call?

Copy the prompt

Copied

Find recordings that mention the migration timeline.

Copy the prompt

Copied

Pull the transcript for yesterday's onboarding call.

Highlights

Copy the prompt

Copied

List the highlights tagged as objections this month.

Copy the prompt

Copied

Which calls have no highlights yet?

Copy the prompt

Copied

Summarize the key moments from the QBR recording.

Workspace ops

Copy the prompt

Copied

List recordings shared with the sales team this week.

Copy the prompt

Copied

Which webhooks are registered on the workspace?

Copy the prompt

Copied

How many recordings were added in the last 30 days?

SEE HOW AUTH WORKS

Users authorize Grain once. Their credentials stay vaulted, every call is checked, and every action is logged.

Authorize

Your user connects

Grain

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

Grain

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

Grain

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

Grain

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

Same per-user auth pattern across other agents and MCP connectors. Working code, live demos, fork what fits.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

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.

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.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential so attribution, audit, and scope stay accurate.

// shared token
audit → bot_service_account
user_filter → broken

// scalekit
audit → user_abc
scope → enforced ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Grain 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 Grain as the user or as a shared key?

As the user. Each member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Grain bearer token credential 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 is allowed to do in Grain?

Yes. Pass a tool name filter to listScopedTools so the meeting intelligence agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Grain.

What happens when a user revokes Grain 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.

Can the agent read recordings the user cannot open in Grain?

No. Grain scopes recordings by workspace and sharing rules, and the connector calls as the authorizing user, so a rep sees their own and team-shared calls only. Private recordings from other members stay out of reach.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit