PredictLeads connector for AI agents

Tools your account research agent reaches for on PredictLeads, scoped per user.

CALL ANY TOOL

35 tools for company signals in PredictLeads: read job openings, financing events, news, technologies, products, SEC filings, and connections for one company, discover companies and signals across all companies, and follow companies.

predictleads_discover_companies

Discover companies

Find companies by location, employee-count range, NAICS codes, industry or revenue range, most recently updated first. Returns a page of company records (id, domain, name, description, location); meta.count holds an estimated total when page is sent. Use this to build a company list from filters. Use predictleads_get_company when you know the domain, and predictleads_discover_extended_companies for the same search with headcount and industry data.

Parameters

Name

Type

Required

Description

industry

string

Optional

Only return companies that work in this industry. Example: Retail.

limit

integer

Optional

Number of results per page. PredictLeads defaults to 30 and allows at most 1000. Example: 50.

location

string

Optional

Only return companies in this country name or state name/abbreviation. Example: United States.

naics_codes

string

Optional

Comma-separated list of NAICS industry codes for companies, with no spaces. Use 2- to 6-digit NAICS codes from census.gov/naics. Example: 5112,541511.

page

integer

Optional

Page number to return, starting at 1. When you send page, the response also includes the total result count in meta.count; PredictLeads leaves the count out when page is not sent. Example: 2.

revenue_range_high

integer

Optional

Only return companies with revenue equal to or lower than this amount. Example: 100000000.

revenue_range_low

integer

Optional

Only return companies with revenue equal to or higher than this amount. Example: 1000000.

sizes

string

Optional

Comma-separated list of employee-count ranges for companies, with no spaces. Valid values: 1, 2-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+. Example: 51-200,201-500.

predictleads_discover_companies_by_technology

Discover companies by technology

Find companies that use one technology, by technology ID or name, newest detections first, optionally filtered by company location, size or NAICS codes. Returns technology detections with first and last seen dates and score, the companies using it in included, and an estimated total in meta.count when page is sent. Use this for technology-based prospect lists. Use predictleads_list_company_technology_detections for one company's stack. If the technology name is ambiguous, get its ID first with predictleads_list_technologies.

Parameters

Name

Type

Required

Description

technology_id_or_fuzzy_name

string

Required

Technology to match, as its PredictLeads technology ID (a UUID) or its name, matched fuzzily. Use the ID from predictleads_list_technologies for multi-word or ambiguous names. Example: hubspot.

company_location

string

Optional

Only return companies in this country name or state name/abbreviation. Example: United States.

company_naics_codes

string

Optional

Comma-separated list of NAICS industry codes for companies, with no spaces. Use 2- to 6-digit NAICS codes from census.gov/naics. Example: 5112,541511.

company_sizes

string

Optional

Comma-separated list of employee-count ranges for companies, with no spaces. Valid values: 1, 2-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+. Example: 51-200,201-500.

first_seen_at_from

string

Optional

Only return technology detections first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

first_seen_at_until

string

Optional

Only return technology detections first seen before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

last_seen_at_from

string

Optional

Only return technology detections last seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

last_seen_at_until

string

Optional

Only return technology detections last seen before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

limit

integer

Optional

Number of results per page. PredictLeads defaults to 30 and allows at most 1000. Example: 50.

page

integer

Optional

Page number to return, starting at 1. When you send page, the response also includes the total result count in meta.count; PredictLeads leaves the count out when page is not sent. Example: 2.

predictleads_discover_extended_companies

Discover extended companies

predictleads_discover_financing_events

Discover financing events

Search financing events (funding rounds) across all companies, optionally filtered by normalized round type, company location, size, NAICS codes or first seen date, most recently updated first. Returns financing events with dates, financing type, amount and source URLs, with the funded companies and investors in included. Use this to find recently funded companies. Use predictleads_list_company_financing_events for one company's rounds.

Parameters

Name

Type

Required

Description

company_location

string

Optional

Only return financing events of companies in this country name or state name/abbreviation. Example: United States.

company_naics_codes

string

Optional

Comma-separated list of NAICS industry codes for companies, with no spaces. Use 2- to 6-digit NAICS codes from census.gov/naics. Example: 5112,541511.

company_sizes

string

Optional

Comma-separated list of employee-count ranges for companies, with no spaces. Valid values: 1, 2-10, 11-50, 51-200, 201-500, 501-1000, 1001-5000, 5001-10000, 10001+. Example: 51-200,201-500.

financing_types_normalized

string

Optional

Comma-separated list of normalized financing types, with no spaces. Values follow the pattern <stage>, <stage>_plus, <stage>_plus_plus, pre_<stage>, a numbered stage and a _bridge suffix, for stages angel, seed and series_a to series_j. Examples of valid values: angel, pre_seed, seed, seed_plus, series_a, series_a1, series_b, series_c_plus, seed_bridge, series_a_bridge. Example: seed,series_a.

first_seen_at_from

string

Optional

Only return financing events first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

first_seen_at_until

string

Optional

Only return financing events first seen before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

limit

integer

Optional

Number of results per page. PredictLeads defaults to 30 and allows at most 1000. Example: 50.

page

integer

Optional

Page number to return, starting at 1. When you send page, the response also includes the total result count in meta.count; PredictLeads leaves the count out when page is not sent. Example: 2.

predictleads_discover_github_repositories

Discover github repositories

predictleads_discover_job_openings

Discover job openings

predictleads_discover_portfolio_companies

Discover portfolio companies

predictleads_discover_products

Discover products

predictleads_discover_public_company_connections

Discover public company connections

predictleads_discover_startup_platform_posts

Discover startup platform posts

predictleads_follow_company

Follow company

predictleads_get_api_subscription

Get api subscription

predictleads_get_company

Get company

predictleads_get_extended_company

Get extended company

predictleads_get_extended_technology_detection

Get extended technology detection

predictleads_get_job_opening

Get job opening

predictleads_get_news_event

Get news event

predictleads_get_product

Get product

predictleads_get_sec_filing

Get sec filing

predictleads_list_api_request_logs

List api request logs

predictleads_list_company_connections

List company connections

predictleads_list_company_financing_events

List company financing events

predictleads_list_company_github_repositories

List company github repositories

predictleads_list_company_job_openings

List company job openings

List one company's job openings, by domain or PredictLeads company ID, optionally filtered by status, category, location or first/last seen dates. Returns job openings with title, normalized title, description, URL, categories, seniority, salary, location, O*NET data, status and first/last seen dates. Use this for one company's hiring signals. Use predictleads_discover_job_openings to search openings across all companies, and predictleads_get_job_opening to fetch one opening by ID.

Parameters

Name

Type

Required

Description

company_id_or_domain

string

Required

Company to look up, as its website domain or its PredictLeads company ID (a UUID). A bare domain works best, without https:// or a path. Example: stripe.com.

active_only

boolean

Optional

Set to true to return only open job openings: not closed, last seen in the past 5 days and found within the last year. Example: true.

categories

string

Optional

Comma-separated list of news event categories, with no spaces. Valid values: acquires, merges_with, sells_assets_to, loses_client, signs_new_client, declares_bankruptcy, files_suit_against, has_issues_with, closes_offices_in, decreases_headcount_by, attends_event, expands_facilities, expands_offices_in, expands_offices_to, increases_headcount_by, opens_new_location, goes_public, has_earnings, has_revenue, has_valuation, invests_into, invests_into_assets, receives_financing, hires, leaves, promotes, retires_from, integrates_with, is_developing, launches, ends_partnership_with, partners_with, receives_award, recognized_as, identified_as_competitor_of, spins_off_company, spins_off_division. Example: receives_financing,launches.

found_at_from

string

Optional

Only return news events found after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

found_at_until

string

Optional

Only return news events found before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25.

limit

integer

Optional

Number of results per page. PredictLeads defaults to 100 and allows at most 1000. Example: 50.

location

string

Optional

Only return news events in this country name or state name/abbreviation. Example: United States.

page

integer

Optional

Page number to return, starting at 1. When you send page, the response also includes the total result count in meta.count; PredictLeads leaves the count out when page is not sent. Example: 2.

predictleads_list_company_sec_filings

List company sec filings

predictleads_list_company_subpages

List company subpages

predictleads_list_company_technology_detections

List company technology detections

predictleads_list_followed_companies

List followed companies

predictleads_list_similar_companies

List similar companies

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);

// PredictLeads tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["predictleads"], toolNames: [
    "predictleads_list_company_job_openings",
    "predictleads_list_company_financing_events",
    "predictleads_list_company_technology_detections"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Brief me on contoso.com hiring, funding, and tech stack" }] });

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

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Brief me on contoso.com hiring, funding, and tech stack" }],
  tools,
});

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

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Brief me on contoso.com hiring, funding, and tech stack" }],
  tools,
});

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

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

await agent.run("Brief me on contoso.com hiring, funding, and tech stack");

Try these prompts

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

One company

Copy the prompt

Copied

What roles is contoso.com hiring for?

Copy the prompt

Copied

List Northwind's funding rounds.

Copy the prompt

Copied

Which technologies does fabrikam.com use?

Discovery

Copy the prompt

Copied

Find companies that use Snowflake, newest detections first.

Copy the prompt

Copied

Find Series A rounds announced this month.

Copy the prompt

Copied

Show the latest news events across all companies.

Monitoring

Copy the prompt

Copied

Follow contoso.com so its new signals reach our webhooks.

Copy the prompt

Copied

List the companies we follow.

Copy the prompt

Copied

Find companies similar to northwind.io.

SEE HOW AUTH WORKS

Each user connects their own PredictLeads 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

PredictLeads

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

PredictLeads

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

PredictLeads

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

PredictLeads

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 analytics connectors.

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.

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

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.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared PredictLeads API key looks fine in a demo. In production every follow and lookup 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.

PredictLeads 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 PredictLeads as the user or through a shared API key?

As the user. Each user connects their own PredictLeads API key once, and Scalekit sends it with every call. Audit logs attribute every lookup and follow to that user, not a shared service account.

Where is the PredictLeads 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 PredictLeads?

Yes. Filter by tool name in listScopedTools to expose only what you want. Nearly every PredictLeads tool is read-only. The only tools that change the account are predictleads_follow_company and predictleads_unfollow_company; leave them out to keep the agent to research. Scalekit also enforces scope checks before every API call.

What happens when a user revokes PredictLeads 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 does the agent monitor a company with PredictLeads?

predictleads_follow_company follows a company so PredictLeads sends its new signals to the account's webhooks. Webhooks are set up in PredictLeads and need an upgraded plan. predictleads_list_followed_companies shows what the account follows.