> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns. > > **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal): > ```bash > npx -y @scalekit-inc/cli setup -y > ``` > > Global: > ```bash > npm install -g @scalekit-inc/cli > scalekit setup -y > ``` > > Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`. > Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim. > [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/) --- # Connect AI agents to PredictLeads The PredictLeads connector lets your AI agent act in each user's PredictLeads account. Each user connects their own PredictLeads API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 35 tools. **Authentication:** API Key **Categories:** CRM & Sales, Analytics, Marketing **Tools:** 35: 33 read, 1 write, 1 destructive **Users sign in with:** API key **Built by:** Scalekit connector **Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=PREDICTLEADS) ## Setup 1. ### Install the SDK **Node.js** ```bash npm install @scalekit-sdk/node dotenv ``` **Python** ```bash pip install scalekit-sdk-python python-dotenv ``` 2. ### Set your credentials Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**. ```sh title=".env" SCALEKIT_ENVIRONMENT_URL= SCALEKIT_CLIENT_ID= SCALEKIT_CLIENT_SECRET= ``` 3. ### Create the PredictLeads connection In **AgentKit > Connections**, create a PredictLeads connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/). 4. ### Authorize a user and make your first call **Node.js** (`quickstart.mts`) ```typescript import { ScalekitClient } from '@scalekit-sdk/node' import 'dotenv/config' import { createInterface } from 'node:readline/promises' const scalekit = new ScalekitClient( process.env.SCALEKIT_ENVIRONMENT_URL, process.env.SCALEKIT_CLIENT_ID, process.env.SCALEKIT_CLIENT_SECRET, ) const actions = scalekit.actions const connector = 'predictleads' const identifier = 'user_123' // Generate an authorization link for the user const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier }) console.log('Authorize PredictLeads:', link) const rl = createInterface({ input: process.stdin, output: process.stdout }) await rl.question('Press Enter after authorizing...') rl.close() // Make your first call const result = await actions.executeTool({ connector, identifier, toolName: 'predictleads_discover_companies', toolInput: {}, }) console.log(result) ``` ```bash npx tsx quickstart.mts ``` **Python** (`quickstart.py`) ```python import os from scalekit import ScalekitClient from dotenv import load_dotenv load_dotenv() scalekit_client = ScalekitClient( env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"), client_id=os.getenv("SCALEKIT_CLIENT_ID"), client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"), ) actions = scalekit_client.actions connection_name = "predictleads" identifier = "user_123" # Generate an authorization link for the user link_response = actions.get_authorization_link( connection_name=connection_name, identifier=identifier, ) print("Authorize PredictLeads:", link_response.link) input("Press Enter after authorizing...") # Make your first call result = actions.execute_tool( tool_input={}, tool_name="predictleads_discover_companies", connection_name=connection_name, identifier=identifier, ) print(result) ``` ```bash python quickstart.py ``` Each user opens the link once and enters their PredictLeads credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses. ## Tools Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool). **Node.js** ```typescript const result = await actions.executeTool({ toolName: 'predictleads_discover_companies', toolInput: {}, connector: 'predictleads', identifier: 'user_123', }) ``` **Python** ```python result = actions.execute_tool( tool_name="predictleads_discover_companies", tool_input={}, connection_name="predictleads", identifier="user_123", ) ``` `result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call. ### `predictleads_discover_companies` Discover Companies · Read-only 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. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{}` ### `predictleads_discover_companies_by_technology` Discover Companies by Technology · Read-only 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. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{"technology_id_or_fuzzy_name":""}` ### `predictleads_discover_extended_companies` Discover Extended Companies · Read-only Find companies by location, employee-count range, NAICS codes, industry or revenue range, returning extended profiles, most recently updated first. Returns a page of extended company records with employee range, industry, company type, headquarters and funding data. Use this when the list needs firmographics. Use predictleads_discover_companies for the lighter company records. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{}` ### `predictleads_discover_financing_events` Discover Financing Events · Read-only 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. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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 , _plus, _plus_plus, pre_, 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. Example input: `{}` ### `predictleads_discover_github_repositories` Discover GitHub Repositories · Read-only List GitHub repositories of all companies, newest first, optionally filtered by first seen date. Returns repositories with URL, description and first seen date, with the owning companies in included. Use this to find companies that recently published repositories. Use predictleads_list_company_github_repositories for one company. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `first_seen_at_from` (`string`, optional): Only return GitHub repositories first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return GitHub repositories 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. Example input: `{}` ### `predictleads_discover_job_openings` Discover Job Openings · Read-only Search job openings across all companies by O*NET occupation code, title words, seniority, location, active status or found date. Only openings found in the last year are returned. Returns job openings with title, description, URL, categories, seniority, salary and location, the hiring companies in included, and an estimated total in meta.count when page is sent. Use this to find companies hiring for a role. Use predictleads_list_company_job_openings for one company's openings. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `found_at_from` (`string`, optional): Only return job openings found after 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. - `location` (`string`, optional): Only return job openings in this country name or state name/abbreviation. Example: United States. - `onet_codes` (`string`, optional): Comma-separated list of O*NET occupation codes, with no spaces. Find codes at onetonline.org/find/all, for example 41-4011.00 for technical sales representatives. Example: 41-4011.00,11-2021.00. - `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. - `seniority` (`string`, optional): Only return job openings with this seniority. One of: not_set, founder, c_level, partner, president, vice_president, head, director, manager, mid_senior, junior. Example: director. One of: `not_set`, `founder`, `c_level`, `partner`, `president`, `vice_president`, `head`, `director`, `manager`, `mid_senior`, `junior`. - `title` (`string`, optional): Only return job openings whose titles contain all of these words. Example: product manager. Example input: `{}` ### `predictleads_discover_news_events` Discover News Events · Read-only Search news events across all companies, newest first, optionally filtered by category, company location or company size. Returns news events with category, summary, headline, found date and event details, with the companies involved in included. Use this to find companies with a given kind of event, such as new funding or new hires. Use predictleads_list_company_news_events for one company's events. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `company_location` (`string`, optional): Only return events about companies in this country name or state name/abbreviation. Example: United States. - `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. - `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. Example input: `{}` ### `predictleads_discover_portfolio_companies` Discover Portfolio Companies · Read-only List portfolio companies found on the portfolio pages of VCs, accelerators and incubators, as investor connections, newest first. Returns connections with category investor, source URL, context and first/last seen dates, with the investor and the portfolio company in included. Use this to find newly listed portfolio companies across investors. Use predictleads_list_company_connections for one company's investors and partners. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `first_seen_at_from` (`string`, optional): Only return connections first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return connections first seen before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `last_seen_at_from` (`string`, optional): Only return connections last seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `last_seen_at_until` (`string`, optional): Only return connections 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. Example input: `{}` ### `predictleads_discover_products` Discover Products · Read-only Search products, services and solutions across all companies, most recently seen first, optionally filtered by category or subcategory. Returns products with category, subcategory, name, description and source URL, with the offering companies in included. Use this to browse products across companies. Use predictleads_list_company_products for one company's products. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `categories` (`string`, optional): Comma-separated list of product categories, with no spaces. Valid values: product, service, solution, unclassified. Example: product,service. - `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. - `subcategories` (`string`, optional): Comma-separated list of product subcategories, with no spaces. Valid values: industry, use_case, pricing_tier, unclassified. Example: use_case,pricing_tier. Example input: `{}` ### `predictleads_discover_public_company_connections` Discover Public Company Connections · Read-only List the vendor and partner connections of publicly traded companies, newest first. Returns connections with category (vendor or partner), source URL, context and first/last seen dates, with both companies in included. Use this to find vendors and partners of public companies. Use predictleads_list_company_connections for one company's connections. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `first_seen_at_from` (`string`, optional): Only return connections first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return connections 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. Example input: `{}` ### `predictleads_discover_startup_platform_posts` Discover Startup Platform Posts · Read-only List the latest posts on startup platforms (Hacker News Show and Jobs pages) by companies that are hiring or launching products. Returns posts with published date, post type, post URL, company domain, company name and whether the company match is fuzzy. Use this to find early-stage companies launching or hiring. Use predictleads_discover_job_openings for job openings found on company websites. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `post_types` (`string`, optional): Comma-separated list of post types (show_hn = Hacker News Show page, job_hn = Hacker News Jobs page), with no spaces. Valid values: show_hn, job_hn. Example: show_hn,job_hn. - `published_at_from` (`string`, optional): Only return posts published after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `published_at_until` (`string`, optional): Only return posts published before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. Example input: `{}` ### `predictleads_get_api_subscription` Get API Subscription · Read-only Get the PredictLeads API subscription for the connected credentials. Returns the subscription status, the monthly credit quota and the credits used this month. Use this to check remaining credits before large requests. Use predictleads_list_api_request_logs to see which requests used them. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: none. Example input: `{}` ### `predictleads_get_company` Get Company · Read-only Get the PredictLeads company profile for one company, by domain or PredictLeads company ID. Returns the company's id, domain, name, ticker, description, language, location and last extraction states, with parent, subsidiary and similar companies in included. Use this to resolve a domain to a PredictLeads company. Use predictleads_get_extended_company for headcount, industry and social profile data, and predictleads_discover_companies to find companies by filters. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{"company_id_or_domain":""}` ### `predictleads_get_extended_company` Get Extended Company · Read-only Get the extended PredictLeads profile for one company, by domain or PredictLeads company ID. Returns the basic company profile plus employee range, logo, slogan, industry, company type, headquarters, founding year, specialties, last funding round and social profile links. Use this when you need firmographics. Use predictleads_get_company for the basic profile only. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{"company_id_or_domain":""}` ### `predictleads_get_extended_technology_detection` Get Extended Technology Detection · Read-only Get one technology detection with the evidence behind it, by detection ID. Returns the detection's first and last seen dates, score and source count, with the subpages, job openings, DNS records, reviews and connections it was seen on, and competing technology detections, in included. Use this to see why PredictLeads believes a company uses a technology. Use predictleads_list_company_technology_detections to list a company's detections. Requires a detection ID, such as the id of a record from predictleads_list_company_technology_detections. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `technology_detection_id` (`string`, required): PredictLeads ID of the technology detection, a UUID. Get it from the id field of a record returned by predictleads_list_company_technology_detections. Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{"technology_detection_id":""}` ### `predictleads_get_job_opening` Get Job Opening · Read-only Get one job opening by its PredictLeads ID. Returns the opening's title, description, URL, categories, seniority, salary, location, O*NET data, status and first/last seen dates, with the hiring company in included. Use this to refresh or expand one opening you already have. Use predictleads_list_company_job_openings or predictleads_discover_job_openings to find openings. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `job_opening_id` (`string`, required): PredictLeads ID of the job opening, a UUID. Get it from the id field of a record returned by predictleads_list_company_job_openings or predictleads_discover_job_openings. Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{"job_opening_id":""}` ### `predictleads_get_news_event` Get News Event · Read-only Get one news event by its PredictLeads ID. Returns the event's category, summary, headline, found date, confidence and event details, with the companies involved and the source article in included. Use this to expand one event you already have. Use predictleads_list_company_news_events or predictleads_discover_news_events to find events. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `news_event_id` (`string`, required): PredictLeads ID of the news event, a UUID. Get it from the id field of a record returned by predictleads_list_company_news_events or predictleads_discover_news_events. Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{"news_event_id":""}` ### `predictleads_get_product` Get Product · Read-only Get one product by its PredictLeads ID. Returns the product's category, subcategory, name, description, sources, source URL and first/last seen dates, with the company in included. Use this to expand one product you already have. Use predictleads_list_company_products or predictleads_discover_products to find products. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `product_id` (`string`, required): PredictLeads ID of the product, a UUID. Get it from the id field of a record returned by predictleads_list_company_products or predictleads_discover_products. Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{"product_id":""}` ### `predictleads_get_sec_filing` Get SEC Filing · Read-only Get one SEC filing by its PredictLeads ID. Returns the filing's form type, filed date, report date, source URL and document content, with the filing company in included. Use this to fetch one filing you already have. Use predictleads_list_company_sec_filings to find filings. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `sec_filing_id` (`string`, required): PredictLeads ID of the SEC filing, a UUID. Get it from the id field of a record returned by predictleads_list_company_sec_filings. Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{"sec_filing_id":""}` ### `predictleads_get_technology` Get Technology · Read-only Get one tracked technology by its PredictLeads ID or name. Returns the technology's id, name, description, categories, parent categories, vendor domain, URL and pricing data, with its vendor company and parent technology in included. Use this to look up one technology. Use predictleads_list_technologies to browse or search technologies by name. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{"technology_id_or_fuzzy_name":""}` ### `predictleads_list_api_request_logs` List API Request Logs · Read-only List API request log entries for the current PredictLeads subscription, optionally filtered by request date. Returns log entries with request time, path, parameters, response code, credits used, duration and source. Use this to audit credit usage. Use predictleads_get_api_subscription for the monthly totals. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `limit` (`integer`, optional): Number of results per page. PredictLeads defaults to 100 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. - `requested_at_from` (`string`, optional): Only return API request logs requested after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `requested_at_until` (`string`, optional): Only return API request logs requested before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. Example input: `{}` ### `predictleads_list_company_connections` List Company Connections · Read-only List one company's business connections found on company websites, by domain or PredictLeads company ID: partners, vendors, integrations, investors, parent companies and more. Returns connections with category, source category, source URL, context, confidence and first/last seen dates, with both companies (and the technology, for integrations) in included. Use this for one company's relationships. Use predictleads_discover_portfolio_companies for VC portfolio links and predictleads_discover_public_company_connections for public companies' vendors and partners. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `categories` (`string`, optional): Comma-separated list of connection categories, with no spaces. Valid values: partner, vendor, integration, investor, parent, rebranding, published_in, badge, other. Example: vendor,partner. - `first_seen_at_from` (`string`, optional): Only return connections first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return connections 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 100 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_financing_events` List Company Financing Events · Read-only List one company's financing events (funding rounds), by domain or PredictLeads company ID, optionally filtered by first seen date. Returns financing events with effective date, found date, financing type, normalized type, amount, normalized amount and source URLs, with investors in included. Use this for one company's funding history. Use predictleads_discover_financing_events to search rounds across all companies. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `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 100 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_github_repositories` List Company GitHub Repositories · Read-only List one company's GitHub repositories, by domain or PredictLeads company ID, optionally filtered by first seen date. Returns repositories with URL, description and first seen date, with activity timeseries datapoints in included. Use this for one company's open-source activity. Use predictleads_discover_github_repositories to list repositories across all companies. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `first_seen_at_from` (`string`, optional): Only return GitHub repositories first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return GitHub repositories 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 100 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_job_openings` List Company Job Openings · Read-only 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. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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 job categories, with no spaces. Valid values: administration, consulting, data_analysis, design, directors, education, engineering, finance, healthcare_services, human_resources, information_technology, internship, legal, management, marketing, military_and_protective_services, operations, purchasing, product_management, quality_assurance, real_estate, research, sales, software_development, support, manual_work, food. Example: engineering,sales. - `first_seen_at_from` (`string`, optional): Only return job openings first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return job openings first seen before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `last_seen_at_from` (`string`, optional): Only return job openings last seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `last_seen_at_until` (`string`, optional): Only return job openings 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 100 and allows at most 1000. Example: 50. - `location` (`string`, optional): Only return job openings in this country name or state name/abbreviation. Example: United States. - `not_closed` (`boolean`, optional): Set to true to return job openings that are not closed, without the last-seen check that active_only applies. Example: true. - `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. - `with_description_only` (`boolean`, optional): Set to true to return only job openings that have a description. Example: true. - `with_location_only` (`boolean`, optional): Set to true to return only job openings that have a location. Example: true. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_news_events` List Company News Events · Read-only List one company's news events, by domain or PredictLeads company ID, optionally filtered by category, location or found date. Returns news events with category (such as acquires, receives_financing, hires or launches), summary, headline, found date, confidence and event details such as amount, product or job title, with the other company and source article in included. Use this for one company's news signals. Use predictleads_discover_news_events to search events across all companies, and predictleads_get_news_event to fetch one event by ID. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_products` List Company Products · Read-only List the products, services and solutions one company offers, by domain or PredictLeads company ID, as extracted from its website. Returns products with category, subcategory, name, normalized name, description, sources, source URL and first/last seen dates. Use this to see what one company sells. Use predictleads_discover_products to search products across all companies, and predictleads_get_product to fetch one product by ID. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `categories` (`string`, optional): Comma-separated list of product categories, with no spaces. Valid values: product, service, solution, unclassified. Example: product,service. - `first_seen_at_from` (`string`, optional): Only return products first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return products 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 100 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. - `subcategories` (`string`, optional): Comma-separated list of product subcategories, with no spaces. Valid values: industry, use_case, pricing_tier, unclassified. Example: use_case,pricing_tier. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_sec_filings` List Company SEC Filings · Read-only List one public company's SEC filings, by domain or PredictLeads company ID, newest first, optionally filtered by form type or filing date. Returns filings with form type, filed date, report date, source URL and document content. Use this to read a public company's 10-K, 10-Q or 8-K filings. Use predictleads_get_sec_filing to fetch one filing by ID. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `filed_at_from` (`string`, optional): Only return SEC filings filed after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `filed_at_until` (`string`, optional): Only return SEC filings filed before this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `form_types` (`string`, optional): Comma-separated list of SEC form types, with no spaces. Valid values: 6-K, 8-K, 10-K, 10-Q, 20-F, 40-F, 25. Example: 10-K,10-Q. - `limit` (`integer`, optional): Number of results per page. PredictLeads defaults to 10 and allows at most 50. 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_subpages` List Company Website Subpages · Read-only List the website subpages PredictLeads has tracked for one company, by domain or PredictLeads company ID, to follow how its website changes over time. Returns subpages with category (such as pricing, careers, customers, integrations or changelog), URL, text content in Markdown and first/last seen dates. Use this to spot new or changed pages, for example a new pricing or integrations page since a date. Use predictleads_list_company_products for the products and services PredictLeads extracted from the site. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `first_seen_at_from` (`string`, optional): Only return subpages first seen after this date (ISO 8601 date). Format: YYYY-MM-DD. Example: 2024-09-25. - `first_seen_at_until` (`string`, optional): Only return subpages 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 100 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_company_technology_detections` List Company Technology Detections · Read-only List the technologies one company uses, by domain or PredictLeads company ID, as technology detections. Returns detections with first and last seen dates, score, source count and a behind-firewall flag, with each technology (name, categories) in included. Use this for one company's tech stack. Use predictleads_discover_companies_by_technology to find the companies that use a given technology. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `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 100 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_followed_companies` List Followed Companies · Read-only List the companies the PredictLeads account follows. Returns each followed company's domain and the custom company identifier set when it was followed. Use this to see which companies feed PredictLeads webhooks. Use predictleads_follow_company and predictleads_unfollow_company to change the list. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `limit` (`integer`, optional): Number of results per page. PredictLeads defaults to 100 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. Example input: `{}` ### `predictleads_list_similar_companies` List Similar Companies · Read-only List companies similar to one company, by domain or PredictLeads company ID. Returns similarity records with score, position and refresh date, a reason for the top 20, and the similar companies in included. Use this to find lookalike companies for one account. Use predictleads_discover_companies to search by firmographic filters instead. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `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. - `limit` (`integer`, optional): Number of results per page. PredictLeads defaults to 20 and allows at most 50. 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. Example input: `{"company_id_or_domain":""}` ### `predictleads_list_technologies` List Technologies · Read-only List the technologies PredictLeads tracks, optionally filtered by fuzzy name or parent technology. Returns technologies with id, name, description, categories, parent categories, vendor domain, URL, pricing data and created date. Use this to find a technology's ID by name. Use predictleads_get_technology to fetch one technology you already know. Read only: yes. Destructive: no. Idempotent (safe to retry): yes. Inputs: - `fuzzy_name` (`string`, optional): Only return technologies whose name fuzzily matches this text. Example: salesforce. - `limit` (`integer`, optional): Number of results per page. PredictLeads defaults to 100 and allows at most 1000. Example: 50. - `order_by` (`string`, optional): Sort order: created_at_asc, created_at_desc, or fuzzy_score_desc (best name match first; only valid together with fuzzy_name). Example: fuzzy_score_desc. One of: `created_at_asc`, `created_at_desc`, `fuzzy_score_desc`. - `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. - `parent_technology_id` (`string`, optional): Only return technologies whose direct parent is the technology with this ID (UUID). Example: 3f2504e0-4f89-41d3-9a0c-0305e82c3301. Example input: `{}` ### `predictleads_follow_company` Follow Company · Write Follow a company, by domain or PredictLeads company ID, so PredictLeads sends its new signals to the account's webhooks. Returns a success flag. Use this to start monitoring a company. Use predictleads_unfollow_company to stop, and predictleads_list_followed_companies to see the list. Webhooks are set up in PredictLeads on the Trigger Subscriptions page and need an upgraded plan. Read only: no. Destructive: no. Idempotent (safe to retry): no. Inputs: - `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. - `custom_company_identifier` (`string`, optional): Your own identifier for this company, such as a CRM account ID. PredictLeads returns it with the followed company and in webhook payloads. Example: 435366. Example input: `{"company_id_or_domain":""}` ### `predictleads_unfollow_company` Unfollow Company · Destructive Unfollow a company, by domain or PredictLeads company ID, so PredictLeads stops sending its signals to the account's webhooks. Returns a success flag. Use this to stop monitoring a company. Use predictleads_follow_company to follow it again. Read only: no. Destructive: yes. Idempotent (safe to retry): yes. Inputs: - `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. Example input: `{"company_id_or_domain":""}` ## Related Other CRM & Sales connectors ([all 103](/agentkit/connectors/?category=crm-sales)): - [Insightly](/agentkit/connectors/insightly/): Scalekit connector, API key, 108 tools - [HubSpot](/agentkit/connectors/hubspot/): Scalekit connector, OAuth, 457 tools - [Salesforce](/agentkit/connectors/salesforce/): Scalekit connector, OAuth, 74 tools --- ## More Scalekit documentation | Resource | What it contains | When to use it | |----------|-----------------|----------------| | [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content | | [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas | | [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |