ZoomInfo connector for AI agents

Tools your sales agent reaches for on ZoomInfo, scoped per user.

CALL ANY TOOL

15 tools covering company lookalike discovery, GTM Studio management for ICPs, offerings, competitor records, buyer personas, customer settings, and engagement interaction tracking.

zoominfo_archive_buyer_persona

Archive Buyer Persona

Archive a buyer persona to hide it from active use without permanently deleting it. The persona can be unarchived later. Use this instead of delete when you may need to restore the persona.

Parameters

Name

Type

Required

Description

buyerPersonaId

string

Required

UUID of the buyer persona.

schema_version

string

Optional

Schema version override

tool_version

string

Optional

Tool version override

zoominfo_archive_competitor

Archive Competitor

zoominfo_archive_offering

Archive Offering

zoominfo_archive_segment

Archive Segment

zoominfo_ask_account_summary

Ask Account Summary

zoominfo_create_audience

Create Audience

zoominfo_create_audience_columns

Create Audience Columns

zoominfo_create_folder

Create Folder

zoominfo_create_marketing_audience

Create Marketing Audience

zoominfo_delete_audience

Delete Audience

zoominfo_delete_audience_column

Delete Audience Column

zoominfo_delete_audience_rows

Delete Audience Rows

zoominfo_delete_buyer_persona

Delete Buyer Persona

zoominfo_delete_competitor

Delete Competitor

zoominfo_delete_content_interaction

Delete Content Interaction

zoominfo_delete_folder

Delete Folder

zoominfo_delete_marketing_audience

Delete Marketing Audience

zoominfo_delete_offering

Delete Offering

zoominfo_delete_segment

Delete Segment

zoominfo_delete_settings

Delete Settings

zoominfo_enrich_audience

Enrich Audience

zoominfo_enrich_companies

Enrich Companies

zoominfo_enrich_contacts

Enrich Contacts

zoominfo_enrich_corporate_hierarchy

Enrich Corporate Hierarchy

zoominfo_enrich_hashtags

Enrich Hashtags

zoominfo_enrich_intent

Enrich Intent

zoominfo_enrich_news

Enrich News

zoominfo_enrich_org_charts

Enrich Org Charts

zoominfo_enrich_scoops

Enrich Scoops

zoominfo_enrich_technologies

Enrich Technologies

For more tools, view docs.

Build your Agent

Same auth pattern across every framework.

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);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["zoominfo"] }, pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find verified contacts at Acme Corp." }] });

import { ScalekitClient } from "@scalekit-sdk/node";
import OpenAI from "openai";

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Enrich acme.com with firmographics." }],
  tools,
});
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import { ScalekitClient } from "@scalekit-sdk/node";
import Anthropic from "@anthropic-ai/sdk";

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull the org chart for Acme Corp." }],
  tools,
});
await sk.tools.executeTool(msg.content, "user_123");

import { ScalekitClient } from "@scalekit-sdk/node";
import { Agent } from "@google/adk/agents";

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

const agent = new Agent({
  name: "zoominfo_prospecting_agent",
  model: "gemini-2.5-pro",
  instruction: "Research companies and contacts for the signed-in user.",
  tools,
});
await agent.run("Which accounts changed CEOs this quarter?");

Try these prompts

Paste any prompt into your agent to get started.

Prospect research

Copy the prompt

Copied

Find verified contacts at Acme Corp with direct dials.

Copy the prompt

Copied

Pull the org chart for our top target account.

Copy the prompt

Copied

Which fintech companies added 50 or more engineers this year?

Account enrichment

Copy the prompt

Copied

Enrich acme.com with firmographics and technographics.

Copy the prompt

Copied

Update this CRM record with ZoomInfo company data.

Copy the prompt

Copied

What intent signals fired for my named accounts this week?

Territory planning

Copy the prompt

Copied

List companies in my territory with over 500 employees.

Copy the prompt

Copied

Find lookalikes of our 10 best customers.

Copy the prompt

Copied

Which accounts changed CEOs this quarter?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

ZoomInfo

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

ZoomInfo

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

ZoomInfo

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

ZoomInfo

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

CRM AI agent

Log calls, update opportunity stages, and surface stalled deals across HubSpot or Salesforce. No manual data entry.

HubSpot

Salesforce

View agent

SALES

Deal intelligence agent

Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared ZoomInfo token looks fine in a demo. In production every call looks like one service account, and you cannot tell who did what. 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.

ZoomInfo 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 connect to ZoomInfo using an API key or OAuth?

ZoomInfo uses API key authentication. Scalekit stores the API key in its encrypted vault and injects it at request time. The key is never written into LLM context, agent memory, or logs — the agent calls ZoomInfo tools without ever seeing the credential directly.

What data can the agent access through the ZoomInfo MCP server?

The agent can search for companies and contacts, retrieve firmographic data (industry, revenue, headcount, location), technographic data (tools and technologies in use), and enrich CRM records with verified business information. Access is scoped to the data products included in your ZoomInfo subscription.

Are any ZoomInfo actions irreversible? Can the agent write or modify data?

ZoomInfo MCP tools are primarily read-only — searching, looking up, and enriching are non-destructive operations. If your integration includes CRM enrichment writes, those updates are applied to your CRM records and cannot be automatically undone. Use listScopedTools to restrict the agent to read-only tools if you want to prevent any write operations.

How does Scalekit secure the ZoomInfo API key?

Scalekit vaults the ZoomInfo API key with AES-256 encryption at rest. The key is resolved at request time per tool call and is never surfaced to the LLM, stored in agent memory, or written to logs. You can rotate or revoke the key from the Scalekit dashboard at any time, and the change takes effect immediately on the next call.

ZoomInfo charges per credit for certain data lookups. Can the agent exhaust my credit balance?

Yes — bulk enrichment or high-frequency contact lookups can consume credits quickly. You can limit exposure by using listScopedTools to restrict the agent to lower-cost search tools and blocking direct export or bulk-enrich tools. It is also good practice to set usage alerts in your ZoomInfo account so you are notified before credits run low.

On this page

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