Ocean.io connector for AI agents

Tools your account discovery agent reaches for on Ocean.io, scoped per user.

CALL ANY TOOL

32 tools for account discovery in Ocean.io: search lookalike companies and people, enrich them in bulk, read LinkedIn posts, comments, and reactions, segment domains, and manage exclusion lists.

ocean_add_exclusion_list_items

Add exclusion list items

Add company domains or LinkedIn handles to an exclusion list, creating the list when no listId is given. Returns the listId of the updated or new list. Use this tool to keep known companies or people out of search results. Use ocean_create_exclusion_list to create an empty list.

Parameters

Name

Type

Required

Description

items

array

Required

Company domains or LinkedIn handles to add, up to 10,000 per request. Items are company domains in a companies list and LinkedIn handles in a people list. A URL is reduced to its domain or LinkedIn handle (`https://www.linkedin.com/in/john-doe/` is stored as `john-doe`).

type

string

Required

Whether the list holds people (LinkedIn handles) or companies (domains). One of: `people`, `companies`.

listId

string

Optional

List to add items to. A new list is created when omitted.

ocean_add_marked_domains

Add marked domains

ocean_attribute_segmentation_domains

Attribute segmentation domains

ocean_autocomplete_companies

Autocomplete companies

ocean_autocomplete_job_titles

Autocomplete job titles

ocean_autocomplete_keywords

Autocomplete keywords

ocean_autocomplete_locations

Autocomplete locations

ocean_create_exclusion_list

List create exclusion

ocean_create_segmentation

Create segmentation

ocean_delete_exclusion_list

List delete exclusion

ocean_enrich_company

Enrich company

ocean_enrich_person

Enrich person

ocean_get_company_posts

Get company posts

ocean_get_credit_balance

Get credit balance

ocean_get_data_fields

Get data fields

ocean_get_exclusion_list

List get exclusion

ocean_get_person_posts

Get person posts

ocean_get_post_comments

Get post comments

ocean_get_post_reactions

Get post reactions

ocean_get_post_reshares

Get post reshares

ocean_get_segmentation

Get segmentation

ocean_list_exclusion_lists

List exclusion lists

ocean_lookup_companies

Lookup companies

ocean_lookup_people

Lookup people

ocean_preview_search_companies

Preview search companies

ocean_preview_search_people

Preview search people

Preview a people search with company information, returning a small sample. Returns the total number of available people, a sample of up to 50 people, and credits used. Use this tool to size a contact audience cheaply before running ocean_search_people. Available to enterprise API customers only.

Parameters

Name

Type

Required

Description

companiesFilters

object

Optional

Company filters as a JSON object. Common filters are lookalikeDomains (up to 10 seed domains), includeDomains, excludeDomains, companySizes (ranges such as 11-50 or 51-200), revenues (ranges such as 10-50M), industries, industryCategories, linkedinIndustries, keywords (lists named anyOf, allOf and noneOf), technologies, primaryLocations, yearFounded and employeeCountOcean (each with from and to), fundingRound, headcountGrowth, jobPostings, buyingSignals and excludeListId. Valid industry, technology and region values come from Get Data Fields. Example: {"lookalikeDomains": ["stripe.com"], "companySizes": ["51-200", "201-500"]}.

fields

array

Optional

Person fields to return in the sample. If omitted, Ocean.io returns its default field set.

jobTitleThreshold

number

Optional

Threshold for job title similarity. The value must be between 0 and 1. Default is 0.8

peopleFilters

object

Optional

People filters as a JSON object. Common filters are seniorities, departments (an object with a departments list and an optional mode), jobTitleKeywords (lists named anyOf, allOf and noneOf), countries (ISO alpha-2 codes), skills, names, includeLinkedinHandles, includePeopleIds, excludeLinkedinHandles, excludePeopleIds, excludeListId, lookalikeLinkedinHandles, updatedWithinMonths and fieldsExist. Valid seniority and department values come from Get Data Fields. Example: {"seniorities": ["C-Level", "VP"], "jobTitleKeywords": {"anyOf": ["marketing"]}}.

peoplePerCompany

integer

Optional

Number of people to return per company. If you want to return all people from a company, don't set this value.

searchAfter

string

Optional

Use `searchAfter` returned by the previous request to get the next page.

size

integer

Optional

Number of sample people to return, from 1 to 50.

ocean_remove_exclusion_list_items

Remove exclusion list items

ocean_rename_exclusion_list

List rename exclusion

ocean_search_companies

Search companies

Search Ocean.io's company database with filters or lookalike seed domains. Returns matching companies, the total count, credits used, and a searchAfter cursor for the next page. Use this tool to find new target accounts. Use ocean_lookup_companies when the exact domains are already known. Consumes Ocean.io credits. Call ocean_get_data_fields first to get valid industry, technology and region values.

Parameters

Name

Type

Required

Description

companiesFilters

object

Optional

fields

array

Optional

Company fields to return, such as domain, name, industries and companySize. If omitted, Ocean.io returns its default field set; requesting fewer fields gives faster responses.

peopleFilters

object

Optional

searchAfter

string

Optional

Use `searchAfter` returned by the previous request to get the next page

size

integer

Optional

Number of companies to return, from 1 to 10,000. Use searchAfter to page beyond 10,000 results.

ocean_search_people

Search people

Search Ocean.io's people database with filters, lookalike LinkedIn handles, or specific person ids. Returns matching people with profile and company details, the total count, credits used, and a searchAfter cursor for the next page. Use this tool to find contacts at target companies. Use ocean_lookup_people when LinkedIn handles or Ocean ids are already known. Consumes Ocean.io credits. Call ocean_get_data_fields first to get valid seniority and department values.

Parameters

Name

Type

Required

Description

companiesFilters

object

Optional

fields

array

Optional

Person fields to return, such as name, jobTitle, linkedinUrl and seniorities. Company details use the company. prefix. If omitted, Ocean.io returns its default field set.

jobTitleThreshold

number

Optional

Job title similarity threshold between 0 and 1. Higher values match titles more strictly. Ocean.io uses 0.8 when unset.

peopleFilters

object

Optional

peoplePerCompany

integer

Optional

Maximum number of people to return per company. Leave unset to return every matching person at each company.

searchAfter

string

Optional

Use `searchAfter` returned by the previous request to get the next page.

size

integer

Optional

Number of people to return, from 1 to 10,000.

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);

// Ocean.io tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["ocean"], toolNames: [
    "ocean_search_companies",
    "ocean_search_people",
    "ocean_enrich_company"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find companies like northwind.io in Germany and their heads of RevOps" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find companies like northwind.io in Germany and their heads of RevOps" }],
  tools,
});

// Execute the tool call with the user's vaulted Ocean.io API key
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: ["ocean"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find companies like northwind.io in Germany and their heads of RevOps" }],
  tools,
});

// Tool call runs with the user's vaulted Ocean.io API key
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: ["ocean"] }, pageSize: 100,
});

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

await agent.run("Find companies like northwind.io in Germany and their heads of RevOps");

Try these prompts

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

Lookalike search

Copy the prompt

Copied

Find companies like northwind.io and contoso.com in Germany.

Copy the prompt

Copied

Preview how many heads of RevOps work at those companies.

Copy the prompt

Copied

Suggest valid job titles that start with Head of Rev.

Enrichment

Copy the prompt

Copied

Enrich these 200 domains with company size and industry.

Copy the prompt

Copied

Enrich the person behind this LinkedIn handle.

Copy the prompt

Copied

How many Ocean.io credits do I have left?

Signals and lists

Copy the prompt

Copied

Show the latest LinkedIn posts from Contoso's company page.

Copy the prompt

Copied

Add our current customers' domains to an exclusion list.

Copy the prompt

Copied

Segment these 500 domains and show which segment each one fits.

SEE HOW AUTH WORKS

Each user connects their own Ocean.io API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Ocean.io

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

Ocean.io

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

Ocean.io

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

Ocean.io

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 marketing 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

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 Ocean.io API key looks fine in a demo. In production every search and list 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 key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Ocean.io 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 Ocean.io as the user or through a shared API key?

As the user. Each user connects their own Ocean.io API key once, and Scalekit sends it with every call. Audit logs attribute every search, enrichment, and list change to that user, not a shared service account.

Where is the Ocean.io API key stored?

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

Can I limit what the agent does in Ocean.io?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example search and enrichment without ocean_delete_exclusion_list, which deletes a list and all of its items. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Ocean.io 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.

How can the agent size an Ocean.io search before running it?

It can call ocean_preview_search_companies or ocean_preview_search_people first, which return the total number of matches and a small sample, then run the full search. ocean_get_credit_balance shows the remaining credits.