Momentum connector for AI agents

CALL ANY TOOL

List meetings, read the revenue signals extracted from them, and ingest new recordings with the signed-in user's own Momentum access.

momentum_ingest_meeting

Ingest meeting

Ingest a meeting (and optional transcript) from any source into Momentum. Requires the meeting title, start_time, end_time, host_name, host_email, and process_imported_meeting. Optionally include attendees, a transcript (as ordered segments), Salesforce record IDs, and source URLs. The request body must not exceed 5 MB. Note: this endpoint targets Momentum's ingestion receiver host.

Parameters

Name

Type

Required

Description

end_time

string

Required

End time of the meeting in ISO 8601 format. Example: 2025-01-15T10:30:00Z.

host_email

string

Required

Email address of the meeting host.

host_name

string

Required

Name of the meeting host.

process_imported_meeting

boolean

Required

Whether Momentum should process the imported meeting (e.g. run summaries and AI signals) after ingestion.

start_time

string

Required

Start time of the meeting in ISO 8601 format. Example: 2025-01-15T10:00:00Z.

title

string

Required

Title of the meeting.

attendees

array

Optional

List of meeting attendees. Each attendee may include email, name, and is_internal (whether the attendee belongs to your organization).

call_url

string

Optional

URL to join the meeting.

external_id

string

Optional

Optional external meeting ID from the source system.

recording_url

string

Optional

URL to the meeting recording.

salesforce_account_id

string

Optional

Salesforce Account ID to associate with the meeting.

salesforce_opportunity_id

string

Optional

Salesforce Opportunity ID to associate with the meeting.

transcript_segments

array

Optional

Optional ordered transcript for the meeting. Each segment requires text and timestamp_seconds (offset in seconds from the meeting start) and may include speaker_name.

momentum_list_meetings

List meetings

momentum_list_signal_definitions

List signal definitions

momentum_list_signal_executions

List signal executions

momentum_list_signal_prompts

List signal prompts

momentum_list_signal_v2_executions

List signal v2 executions

momentum_list_users

List users

momentum_remap_meeting

Remap meeting

Associate a meeting with new Salesforce objects (account, opportunity, and/or lead) and optionally trigger call summary generation and AI signals. You must identify the meeting in exactly one of two ways: (1) by external source — provide source_id and source_type; or (2) by meeting details — provide either momentum_meeting_id alone, OR the combination of meeting_title, meeting_start_time, and meeting_host_email. At least one Salesforce record ID (opportunity, account, or lead) is required.

Parameters

Name

Type

Required

Description

meeting_host_email

string

Optional

Email of the meeting host. Provide together with meeting_title and meeting_start_time.

meeting_start_time

string

Optional

Start time of the meeting in ISO 8601 format. Provide together with meeting_title and meeting_host_email.

meeting_title

string

Optional

Title of the meeting. Provide together with meeting_start_time and meeting_host_email to identify the meeting by details (when not using momentum_meeting_id or source).

momentum_meeting_id

integer

Optional

Internal Momentum meeting ID. When provided, identifies the meeting directly and no other meeting-detail fields are needed. Do not combine with source_id/source_type.

salesforce_account_id

string

Optional

Salesforce account ID to associate with the meeting. At least one of salesforce_opportunity_id, salesforce_account_id, or salesforce_lead_id is required.

salesforce_lead_id

string

Optional

Salesforce lead ID to associate with the meeting. At least one of salesforce_opportunity_id, salesforce_account_id, or salesforce_lead_id is required.

salesforce_opportunity_id

string

Optional

Salesforce opportunity ID to associate with the meeting. At least one of salesforce_opportunity_id, salesforce_account_id, or salesforce_lead_id is required.

source_id

string

Optional

Source identifier for the meeting in the external system. Provide together with source_type to identify the meeting by source. Use this OR meeting details, not both.

source_type

string

Optional

Type of meeting source. Provide together with source_id. Valid values: GOOGLE_CALENDAR, ZOOM, RECALL, GONG, CHORUS, WINGMAN, WISER, SALESLOFT.

trigger_ai_signals

boolean

Optional

Whether to trigger AI signals after remapping. Defaults to false.

trigger_summary

boolean

Optional

Whether to trigger call summary generation after remapping. Defaults to false.

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);

// Momentum tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["momentum"], toolNames: [
    "momentum_ingest_meeting",
    "momentum_list_meetings",
    "momentum_list_signal_definitions"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Is the Salesforce sync healthy?" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which data sources are connected?" }],
  tools,
});

// Execute the tool call with the user's vaulted Momentum credential
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: ["momentum"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull open Zendesk tickets created this week." }],
  tools,
});

// Tool call runs with the user's vaulted Momentum credential
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: ["momentum"] }, pageSize: 100,
});

const agent = new Agent({
  name: "momentum_agent",
  model: "gemini-2.5-pro",
  instruction: "Work with Momentum for the signed-in user.",
  tools,
});

await agent.run("What auth does the Shopify connector need?");

Try these prompts

Paste any prompt into your agent to get started.

Signal review

Copy the prompt

Copied

What signals fired on my calls this week?

Copy the prompt

Copied

Show me every call where a competitor was mentioned.

Copy the prompt

Copied

List the signal definitions configured for our team.

Meeting recall

Copy the prompt

Copied

List my meetings from the last seven days.

Copy the prompt

Copied

Which meetings have no next step recorded?

Copy the prompt

Copied

Remap this meeting to the right opportunity.

Team coverage

Copy the prompt

Copied

List the users on our Momentum workspace.

Copy the prompt

Copied

Which reps had the most signals fire last month?

Copy the prompt

Copied

Show me the signal prompts behind the budget signal.

SEE HOW AUTH WORKS

Your users connect Momentum once. Their credentials stay vaulted, every call is scope checked, and every action is logged.

1

Authorize

Your user connects

Momentum

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

Momentum

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

Momentum

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

Momentum

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 connectors.

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

Revenue forecast commentary

Pulls open pipeline from Salesforce and HubSpot, calculates coverage against quota, flags at-risk stages, posts commentary to Slack, and logs every snapshot to Google Sheets.

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

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Test other agents

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

SALES

Deal intelligence agent

Score Gong call risk with an LLM, cross-reference the Attio record, and DM each owner their at-risk deals in Slack.

GTM

Revenue forecast agent

Score pipeline coverage against quota across Salesforce and HubSpot, post forecast commentary to Slack, log snapshots to Sheets.

SALES

Sales call prep agent

Read tomorrow's calls from Google Calendar, mine Granola notes and Attio history, and deliver each rep a prep brief in Slack.

OPS

Meeting prep agent

Assemble the agenda, HubSpot attendee history, and open action items from Gmail before every meeting on the calendar.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Momentum token looks fine in a demo. In production every action looks like one service account, and you cannot tell who wired a source or ran a query. 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.

Momentum 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

Can the agent read calls the user was not on?

Only if Momentum already grants that user access. Scalekit resolves their credential rather than a shared workspace key, so agent reach matches human reach.

Is meeting content sent to the model?

Only what your agent asks for. The credential itself is never placed in LLM context; it is resolved at request time behind the tool call.

How many tools does this connector expose?

8, covering meetings, signal definitions, signal executions, prompts, and users.

Can I block the ingest tool?

Yes. Scope the connection to the list and get tools and ingest stays unavailable, enforced before the API call.

How are keys isolated across customers?

Per tenant in an encrypted vault. Cross-tenant resolution is denied at the vault layer, not by convention.

Momentum

Tools your agent reaches for on Momentum, scoped per user.