La Growth Machine connector for AI agents

Tools your outbound agent reaches for on La Growth Machine, scoped per user.

CALL ANY TOOL

46 tools for sales outreach in La Growth Machine: build audiences and import leads, create, update, and enrich leads, run and pause campaigns, edit campaign messages, and read, send, and archive inbox conversations.

lagrowthmachine_add_campaign_step_message

Add campaign step message

Add a message to a campaign step that has no message yet. Returns the new message id, step id, channel, content and subject. Use get_campaign_steps to find steps where hasMessage is false. Use edit_campaign_message to change an existing message.

Parameters

Name

Type

Required

Description

campaign_id

string

Required

ID of the campaign (24-character hex ObjectId). Get it from lagrowthmachine_list_campaigns.

new_html

string

Required

The message body, in the `newHtml` format.

step_id

string

Required

ID of the step, the `stepId` returned by `GET /campaigns/{campaignId}/steps`.

subject_new_html

string

Optional

Email steps only: the subject, as a single `<p>…</p>` containing text, `<var/>` or `<spin>`. Ignored for LinkedIn and Twitter steps.

lagrowthmachine_archive_conversation

Archive conversation

lagrowthmachine_complete_call_manual_task

Complete call manual task

lagrowthmachine_complete_message_manual_task

Complete message manual task

lagrowthmachine_create_audience

Create audience

lagrowthmachine_delete_identity_preference

Delete identity preference

lagrowthmachine_edit_campaign_message

Edit campaign message

lagrowthmachine_enrich_lead

Enrich lead

lagrowthmachine_enrich_linkedin_post

Post enrich linkedin

lagrowthmachine_get_audience

Get audience

lagrowthmachine_get_audience_leads

Get audience leads

lagrowthmachine_get_campaign_lead_stats

Get campaign lead stats

lagrowthmachine_get_campaign_stats

Get campaign stats

lagrowthmachine_get_conversation_messages

Get conversation messages

lagrowthmachine_get_enrich_result

Get enrich result

lagrowthmachine_get_lead_logs

Get lead logs

lagrowthmachine_import_audience_from_linkedin

Import audience from linkedin

lagrowthmachine_list_audiences

List audiences

lagrowthmachine_list_campaigns

List campaigns

lagrowthmachine_list_identities

List identities

lagrowthmachine_list_members

List members

lagrowthmachine_list_public_campaigns

List public campaigns

lagrowthmachine_remove_lead_from_audiences

Remove lead from audiences

lagrowthmachine_search_conversations

Search conversations

Search and filter inbox conversations by text, lead, identity, campaign, audience, status, channel and dates. Returns conversation ids and metadata (lead, identity, last message time, status, type) with total, hasMore and nextToken; no message text. Use to find conversations, then get_conversation_messages to read them. Pass nextToken as search_after for the next page.

Parameters

Name

Type

Required

Description

audience_ids

string

Optional

Only conversations with leads of these audiences. Comma-separated audience IDs.

call_completed_at_from

integer

Optional

Only conversations with a call completed at or after this Unix timestamp in milliseconds.

call_completed_at_to

integer

Optional

Only conversations with a call completed at or before this Unix timestamp in milliseconds.

campaign_ids

string

Optional

Campaign IDs, comma-separated. A campaign filters on its audience and its identity; ignored for each of these when `audienceIds` or `identityIds` is also set. Comma-separated values.

favourite

boolean

Optional

`true`: only the conversations starred by the member. `false` has no effect.

identity_ids

string

Optional

Only conversations of these sending identities. Comma-separated identity IDs.

last_message_at_from

integer

Optional

Only conversations whose last message is at or after this Unix timestamp in milliseconds.

last_message_at_to

integer

Optional

Only conversations whose last message is at or before this Unix timestamp in milliseconds.

last_message_status

string

Optional

Status of the last message, comma-separated. `RECEIVED` = the lead spoke last, `SENT` = you spoke last. Comma-separated values.

last_message_type

string

Optional

Filter by type of the last message. Comma-separated values from LINKEDIN, EMAIL, INFO_TEMPLATE_SNOOZE, LGM, COMMENT, MANUAL_TASK, AUTO_QUALIFY.

lead_ids

string

Optional

Only conversations with these leads. Comma-separated lead IDs.

lead_replied

boolean

Optional

When true, only conversations where the lead replied; when false, only those without a reply.

limit

integer

Optional

Maximum number of items to return. Default: `25`.

perseverance

string

Optional

Reply manager follow-up filter. `PERSEVERED` = conversations already followed up; `TO_PERSEVERE` = open or curious replies still to follow up. Allowed values: PERSEVERED, TO_PERSEVERE. One of: `PERSEVERED`, `TO_PERSEVERE`.

string

Optional

Full-text search on leads (name, company...). Only conversations of the matching leads are returned.

read

boolean

Optional

`false`: unread conversations only; `true`: read ones only.

search_after

string

Optional

Pagination token: pass the nextToken of the previous page, with the same filters and sort.

sort_direction

integer

Optional

Sort direction: -1 for newest first, 1 for oldest first. Allowed values: 1, -1. One of: `1`, `-1`. Default: `-1`.

sort_field

string

Optional

Field to sort by: lastMessageAt, callCompletedAt or snoozeUntil. Allowed values: lastMessageAt, callCompletedAt, snoozeUntil. One of: `lastMessageAt`, `callCompletedAt`, `snoozeUntil`. Default: `lastMessageAt`.

status

string

Optional

Filter by conversation status. Comma-separated values from OPEN, SNOOZED, ARCHIVED.

unsubscribed

boolean

Optional

When true, only conversations with unsubscribed leads.

lagrowthmachine_search_crm

Search crm

lagrowthmachine_send_email_message

Send email message

lagrowthmachine_snooze_conversation

Snooze conversation

lagrowthmachine_unarchive_conversation

Unarchive conversation

lagrowthmachine_update_campaign

Update campaign

lagrowthmachine_update_campaign_status

Update campaign status

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);

// La Growth Machine tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["lagrowthmachine"], toolNames: [
    "lagrowthmachine_list_campaigns",
    "lagrowthmachine_get_campaign_stats",
    "lagrowthmachine_update_campaign_status"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Show stats for the Series A Founders campaign and pause it" }] });

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: ["lagrowthmachine"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Show stats for the Series A Founders campaign and pause it" }],
  tools,
});

// Execute the tool call with the user's vaulted La Growth Machine access 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: ["lagrowthmachine"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show stats for the Series A Founders campaign and pause it" }],
  tools,
});

// Tool call runs with the user's vaulted La Growth Machine access 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: ["lagrowthmachine"] }, pageSize: 100,
});

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

await agent.run("Show stats for the Series A Founders campaign and pause it");

Try these prompts

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

Campaigns

Copy the prompt

Copied

Show performance stats for the Series A Founders campaign.

Copy the prompt

Copied

Pause the Series A Founders campaign.

Copy the prompt

Copied

Duplicate the Series A Founders campaign for seed-stage founders.

Leads and audiences

Copy the prompt

Copied

Create an audience called Seed Founders.

Copy the prompt

Copied

Create or update a lead for jordan@acme.com with their company and job title.

Copy the prompt

Copied

Find a professional email and phone number for this lead.

Inbox

Copy the prompt

Copied

Search inbox conversations with replies from this week.

Copy the prompt

Copied

Send Jordan an email reply with our calendar link.

Copy the prompt

Copied

Snooze this conversation until next Monday.

SEE HOW AUTH WORKS

Each user connects their own La Growth Machine access token once, and Scalekit sends it with every call. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

La Growth Machine

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

La Growth Machine

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

La Growth Machine

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

La Growth Machine

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 sales and outreach connectors.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared La Growth Machine access token looks fine in a demo. In production every LinkedIn message and campaign change 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.

La Growth Machine 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 La Growth Machine as the user or through a shared token?

As the user. Each user connects their own La Growth Machine access token once, and Scalekit sends it with every call. Messages, lead changes, and campaign updates are attributed to that user in your audit trail, not a shared service account.

Where is the La Growth Machine access token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new access token. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in La Growth Machine?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example campaign stats and inbox tools without lagrowthmachine_send_linkedin_message or lagrowthmachine_delete_identity_preference. Scalekit also enforces scope checks before every API call.

What happens when a user revokes La Growth Machine 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.

Does enriching a lead use La Growth Machine credits?

Yes. lagrowthmachine_enrich_lead spends credits to find a professional email, a phone number, or LinkedIn profile fields for a lead, and lagrowthmachine_get_enrich_result reads the result. lagrowthmachine_get_credits shows the workspace's credit balance before you run it.