Segment connector for AI agents

Tools your data ops agent reaches for on Segment, scoped per user.

CALL ANY TOOL

104 tools for customer data in Segment: manage sources, destinations, and warehouses, build audiences and computed traits, edit tracking plans and transformations, and check delivery, usage, and audit events.

segment_audience_create

Create audience

Create an Audience in an Engage Space from a query-language definition. Returns the created Audience with its id. Use segment_audience_create for a new Audience. Use segment_audience_update to change one. Requires Engage with the Audiences feature; get space_id from segment_spaces_list. Rate limit: 50 requests per minute.

Parameters

Name

Type

Required

Description

audience_type

string

Required

Kind of Audience: USERS (profiles), ACCOUNTS (B2B accounts) or LINKED (Linked Audiences built on warehouse entities). Example: USERS. One of: `USERS`, `ACCOUNTS`, `LINKED`.

name

string

Required

Name of the Audience. Example: Recent purchasers.

query

string

Required

Segment query-language (CQL) definition of who is in the Audience, for example event('Order Completed').count() >= 1. Example: event('Order Completed').count() >= 1.

space_id

string

Required

ID of the Engage (Unify) Space. Get it from segment_spaces_list. Example: spa_9aQ1Lj62S4bomZKLF4DPqW.

backfill_event_data_days

integer

Optional

Number of days of event data before creation to include when computing membership. Example: 30.

description

string

Optional

Description of the Audience. Example: Profiles with at least one order.

enabled

boolean

Optional

Whether Segment computes the Audience after creation. Example: true.

filter_by_external_ids

array

Optional

Only consider profiles that have at least one of these external identifier types, for example ["email", "user_id"]. Example: ["email", "user_id"].

include_historical_data

boolean

Optional

Whether events from before the Audience was created count towards membership. Example: true.

target_entity

string

Optional

LINKED audiences only: target entity relationship slug. Use profile to target profiles. Example: profile.

segment_audience_delete

Delete audience

segment_audience_get

Get audience

segment_audience_update

Update audience

segment_audiences_list

List audiences

segment_catalog_sources_list

List catalog sources

segment_computed_trait_get

Get computed trait

segment_delivery_overview_filtered_at_source_get

Get delivery overview filtered at source

Get Delivery Overview counts of events dropped at the Source (schema or Protocols filters). Returns event counts per time bucket, optionally grouped by event, type, discard reason or app version. Use it for source-side filtering. Use segment_delivery_overview_filtered_at_destination_get for destination filters.

Parameters

Name

Type

Required

Description

end_time

string

Required

The ISO8601 formatted timestamp corresponding to the end of the requested time frame, noninclusive. Example: 2026-10-02T00:00:00Z.

granularity

string

Required

Bucket size: MINUTE (window up to 4 hours, starting within the last 48 hours), HOUR (window up to 14 days, starting within the last 30 days) or DAY (window up to 30 days, starting within the last 30 days). Example: DAY. One of: `DAY`, `HOUR`, `MINUTE`.

source_id

string

Required

ID of the Segment Source. Get it from segment_sources_list. Example: qQEHquLrjRDN9j1ByrChyn.

start_time

string

Required

The ISO8601 formatted timestamp corresponding to the beginning of the requested time frame, inclusive. Example: 2026-10-01T00:00:00Z.

filter_app_version

string

Optional

Only include results whose app version matches. Pass one value, or several separated by commas. Example: 1.4.0.

filter_discard_reason

string

Optional

Only include results whose discard reason matches. Pass one value, or several separated by commas. Use a value returned by a previous call grouped by discardReason. Example: discard1.

filter_event_name

string

Optional

Only include results whose event name matches. Pass one value, or several separated by commas. Example: Order Completed.

filter_event_type

string

Optional

Only include results whose event type matches. Pass one value, or several separated by commas. Example: track.

group_by

string

Optional

Dimension to group the results by: eventName, eventType, discardReason, appVersion. One dimension per call. Example: eventName.

pagination_count

integer

Optional

Number of items per page, between 1 and 1000. Defaults to 200. Example: 50. Default: `200`.

pagination_cursor

string

Optional

Page cursor from a previous response's pagination object (its next or previous value). Leave it out for the first page. Example: MA==.

segment_destination_filter_create

Create destination filter

segment_destination_filter_delete

Delete destination filter

segment_destination_filter_get

Get destination filter

segment_destination_filter_preview

Preview destination filter

segment_destination_subscriptions_list

List destination subscriptions

segment_destination_update

Update destination

segment_function_get

Get function

segment_labels_list

List labels

segment_reverse_etl_model_create

Create reverse etl model

segment_reverse_etl_sync_cancel

Cancel reverse etl sync

segment_reverse_etl_sync_trigger

Trigger reverse etl sync

segment_source_connected_destinations_list

List source connected destinations

segment_source_delete

Delete source

segment_source_get

Get source

segment_source_labels_add

Add source labels

segment_sources_list

List sources

segment_tracking_plan_rules_remove

Remove tracking plan rules

segment_tracking_plan_rules_update

Update tracking plan rules

segment_tracking_plan_sources_list

List tracking plan sources

segment_transformation_get

Get transformation

segment_usage_mtu_daily_get

Get usage mtu daily

segment_warehouse_connected_sources_list

List warehouse connected sources

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);

// Segment tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["segment"], toolNames: [
    "segment_sources_list",
    "segment_delivery_overview_failed_delivery_get",
    "segment_destination_update"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find failed deliveries from the iOS source yesterday" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find failed deliveries from the iOS source yesterday" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find failed deliveries from the iOS source yesterday" }],
  tools,
});

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

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

await agent.run("Find failed deliveries from the iOS source yesterday");

Try these prompts

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

Pipelines

Copy the prompt

Copied

List the destinations connected to the web app source.

Copy the prompt

Copied

Turn off the Legacy Webhooks destination.

Copy the prompt

Copied

Show recent sync runs for our warehouse.

Audiences and traits

Copy the prompt

Copied

List the audiences in our Engage space.

Copy the prompt

Copied

Create a computed trait that counts orders in the last 30 days.

Copy the prompt

Copied

Start a manual sync for the Churn Risk Reverse ETL mapping.

Governance and usage

Copy the prompt

Copied

Add an Order Completed rule to the Web tracking plan.

Copy the prompt

Copied

Show event volume for the workspace over the last 7 days.

Copy the prompt

Copied

List Audit Trail events from the last 24 hours.

SEE HOW AUTH WORKS

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

Authorize

Your user connects

Segment

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

Segment

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

Segment

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

Segment

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 analytics and marketing connectors.

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

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 Segment access token looks fine in a demo. In production every source, destination, and audience 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.

Segment 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 Segment as the user or through a shared token?

As the user. Each user connects their own Segment access token once, and Scalekit sends it with every call. Audit logs attribute every source, destination, and audience change to that user, not a shared service account.

Where is the Segment 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 Segment?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example delivery and usage read tools without segment_source_delete or segment_warehouse_delete, which delete permanently. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Segment 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.

Which Segment workspace does the agent act on?

The workspace the user's Segment Public API token belongs to. segment_workspace_get returns its id, name, slug, and region, and every source, destination, audience, and tracking plan tool works inside that workspace.