Integration

PredictLeads integration

PredictLeads is a company intelligence API. Look up a company by domain and read its job openings, technology detections, news events, financing events, SEC filings, connections, products, website subpages and GitHub repositories; discover companies, jobs, news, financings, products and technology users across the whole dataset with filters; follow companies so their updates reach your PredictLeads webhooks (each followed company is billed credits every month); and check your credit usage and request logs. Most calls spend credits from the plan's monthly quota, per response or per record returned (each tool says how many); once the quota is used up every call answers HTTP 402. Authentication is your API key and API token (Your Subscription Plans page), sent in the X-Api-Key and X-Api-Token headers.

Connect PredictLeads How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PredictLeads.Built from the 35 PredictLeads tools below, on the connection you add once.

What you can do with PredictLeads

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Connection, 3 operations

discover_portfolio_companiesDiscover portfolio companiesGETDiscovers portfolio companies listed on the portfolio pages of VCs, accelerators and incubators, as investor connections, newest first. Costs 1 credit per record returned.
discover_public_company_connectionsDiscover public company connectionsGETDiscovers vendor and partner connections of publicly traded companies, newest first (first_seen_at). Costs 1 credit per record returned: keep limit small.
list_company_connectionsList company connectionsGETLists one company's connections (by domain or id): partners, vendors, integrations, investors, parent and more, filterable by category. Costs 1 credit per response.

Job opening, 3 operations

discover_job_openingsDiscover job openingsGETDiscovers job openings across companies by O*NET occupation codes, company location, seniority or title words (last year only), with the recruiter named in each posting when found (personal data). Costs 1 credit per record returned.
get_job_openingGet job openingGETReturns one job opening by id: title, description, location, seniority, categories, salary data when found, the recruiter named in the posting (personal data) and the hiring company. Costs 1 credit.
list_company_job_openingsList company job openingsGETLists one company's job openings (by domain or id), filterable by category, location, dates and active status, each with the recruiter named in the posting when found (personal data). Costs 1 credit per response.

News event, 3 operations

discover_news_eventsDiscover news eventsGETDiscovers news events across companies, filterable by category, company location and size, newest first (found_at). Events can name people (personal data). Costs 1 credit per record returned: keep limit small.
get_news_eventGet news eventGETReturns one news event by id (category, summary, amount, dates, source article and the companies involved); it can name people (personal data). Costs 1 credit.
list_company_news_eventsList company news eventsGETLists one company's news events (by domain or id): acquisitions, hires, expansions, launches, financings and more, filterable by category. Events can name people (personal data). Costs 1 credit per response.

Product, 3 operations

discover_productsDiscover productsGETDiscovers products across companies, filterable by category and subcategory, most recently seen first. Costs 1 credit per record returned: keep limit small.
get_productGet productGETReturns one product by id with its company. Costs 1 credit.
list_company_productsList company productsGETLists one company's products (by domain or id), filterable by category and subcategory. Costs 1 credit per response.

Company, 2 operations

discover_companiesDiscover companiesGETDiscovers companies filtered by location, size, NAICS codes, industry and revenue range, newest updates first. Costs 1 credit per record returned: keep limit small. meta.count is an estimate.
get_companyGet companyGETLooks up one company by domain (or PredictLeads company id): name, ticker, description, language, location data, parent, subsidiaries and similar companies (in included). Costs 1 credit.

Extended company, 2 operations

discover_extended_companiesDiscover extended companiesGETDiscovers companies with the extended profile, filtered by location, size, NAICS codes, industry and revenue range. Costs 2 credits per record returned: keep limit small.
get_extended_companyGet extended companyGETLooks up one company by domain or id with the extended profile (more firmographic attributes than get_company). Costs 2 credits per response.

Financing event, 2 operations

discover_financing_eventsDiscover financing eventsGETDiscovers financing events across all companies, filterable by normalized round type, company location, size and NAICS codes, newest first. Costs 1 credit per record returned.
list_company_financing_eventsList company financing eventsGETLists one company's financing events (by domain or id): round type, amount, date and investors. Costs 1 credit per response.

Follow, 2 operations

follow_companyFollow companyPOSTFollows a company by domain or id, so its updates reach your PredictLeads webhooks. The call is free, but each followed company is then billed credits every month. Optionally attach your own company identifier.
unfollow_companyUnfollow companyDELETEStops following a company (by domain or id): its updates no longer reach your webhooks. Costs 1 credit.

Github repository, 2 operations

discover_github_repositoriesDiscover github repositoriesGETDiscovers GitHub repositories of all companies, newest first (first_seen_at). Costs 1 credit per record returned: keep limit small.
list_company_github_repositoriesList company github repositoriesGETLists one company's GitHub repositories (by domain or id). Costs 1 credit per response.

Sec filing, 2 operations

get_sec_filingGet sec filingGETReturns one SEC filing by id with its company. Costs 1 credit.
list_company_sec_filingsList company sec filingsGETLists one company's SEC filings (by domain or id), newest first, filterable by form type. Costs 1 credit per response.

Technology, 2 operations

get_technologyGet technologyGETReturns one tracked technology by its id or fuzzy name (for example HubSpot): name, categories and parent technology. Costs 3 credits.
list_technologiesList technologiesGETLists the technologies PredictLeads tracks, filterable by fuzzy name or parent technology. Costs 3 credits per record returned: keep limit small.

Technology detection, 2 operations

discover_companies_using_technologyDiscover companies using technologyGETLists the companies using one technology (id or fuzzy name, for example HubSpot) as technology detections, newest first. Costs 1 credit per record returned: keep limit small.
list_company_technology_detectionsList company technology detectionsGETLists the technologies one company uses (by domain or id), as technology detections with first and last seen dates. Costs 1 credit per response.

Api request log, 1 operation

list_api_request_logsList api request logsGETLists your past API requests with the path, parameters, response code and credits each one used. Free.

Api subscription, 1 operation

get_api_subscriptionGet api subscriptionGETReturns your subscription status and monthly credits quota and credits used so far. Free: call it to check the remaining budget before a large discover call.

Extended technology detection, 1 operation

get_extended_technology_detectionGet extended technology detectionGETReturns one technology detection by id with extended details (the company, the technology and where it was seen). Costs 1 credit.

Following, 1 operation

list_followed_companiesList followed companiesGETLists the companies you follow (domain and your custom identifier). Followed companies are the ones whose updates PredictLeads pushes to your webhooks. Costs 1 credit per response.

Similar company, 1 operation

list_similar_companiesList similar companiesGETLists companies similar to one company (by domain or id), with a reason for the top 20. Costs 1 credit per record returned (default 20, at most 50).

Startup platform post, 1 operation

discover_startup_platform_postsDiscover startup platform postsGETDiscovers the latest posts on startup platforms (Show HN, HN hiring) by companies hiring or launching products. Costs 1 credit per record returned.

Subpage, 1 operation

list_company_subpagesList company subpagesGETLists the website subpages PredictLeads found for one company (by domain or id). Costs 1 credit per response.

Use PredictLeads from Claude Code, Cursor or Codex

Connect PredictLeads in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its PredictLeads operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect PredictLeads

Create your workspace
Sign up free. Nothing to install.
Connect PredictLeads once
Add your PredictLeads connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.