llms.txt
# PredictLeads
> PredictLeads provides structured company intelligence data on 120M+ companies globally, built for AI agents and autonomous systems. Data is sourced from public web sources and company websites, organized into datasets including news events, job openings, job signals, technology detections, financing events, SEC filings, products, key customers, similar companies, GitHub repositories, and subpages. Accessible via REST API, Webhooks, Flat Files, and MCP.
## Reference
- [API documentation](https://docs.predictleads.com/)
- [OpenAPI spec (JSON)](https://docs.predictleads.com/schemas/open_api_schema.json)
- [MCP server](https://mcp.predictleads.com/)
## Core datasets
### [Companies](https://docs.predictleads.com/guide/companies_dataset)
Firmographic data on 120M+ companies, including descriptions, tickers, locations, and corporate hierarchies (parent and subsidiary relationships). Optional add-ons include industry classifications, NAICS codes, and revenue estimates.
### [News Events](https://docs.predictleads.com/guide/news_events_dataset)
9M+ signals indexed from 20M+ PR sites, news outlets, and blogs. Categorized into 37 distinct event types: product launches, conference visits, partnerships, funding rounds, expansions, leadership changes, hiring plans, awards, and more. Includes the formatted signal, category, location, investment amounts, source URL, article body, author, and images.
### [Job Openings](https://docs.predictleads.com/guide/job_openings_dataset)
Full job postings from 3M+ companies - 300M+ historical records and 9.8M+ active jobs on average. Includes job descriptions, ONET codes, salary details, and direct links to job pages. Structured with job keywords and categories for filtering.
### [Technology Detections](https://docs.predictleads.com/guide/technology_detections_dataset)
2B+ detections across 99M+ companies, covering 240K+ tracked technologies enriched with pricing data. Sources include job postings, website script tags, DNS records, and product review sites.
### [Financing Events](https://docs.predictleads.com/guide/financing_events_dataset)
Structured funding data organized by round, amount, and date - sourced from millions of news sources. Powers investment tracking and market intelligence workflows.
### [Products](https://docs.predictleads.com/guide/products_dataset)
17M+ offerings across 1.4M+ companies, classified as a product, service, or solution. Each record includes the original name, a normalized English translation, and a concise description. Enables market and competitor analysis.
### [SEC Filings](https://docs.predictleads.com/guide/sec_filings_dataset)
190K+ SEC filings (6-K, 8-K, 10-K, 10-Q, 20-F, 40-F, 25) across 6.5K+ public companies, sourced directly from the SEC. Each record includes the form type, filing date, the date the filing reports on, the source URL of the document, and its full content converted to Markdown. Enables tracking of corporate disclosures and material events.
### [Key Customers](https://docs.predictleads.com/guide/connections_dataset)
345M+ supply chain relationships across 60M+ companies, uncovered by extracting company logos from case studies, testimonials, and customer sections using image recognition. Categorized as customers, vendors, partners, integrations, or investors.
### [Similar Companies](https://docs.predictleads.com/guide/similar_companies_dataset)
Company lookalike data on 18.5M+ companies, including a structured reason why each company is considered similar. Enables finding similar businesses, identifying competitive landscapes, and expanding market opportunities.
### [GitHub Repositories](https://docs.predictleads.com/guide/github_repositories_dataset)
GitHub organization repositories linked to 89K+ companies, covering 455K+ repositories. Includes repository URLs, descriptions, and historical activity timeseries, enabling analysis of open-source presence and developer activity.
### [Subpages](https://docs.predictleads.com/guide/subpages_dataset)
Daily-updated website content from 82M+ company websites, covering 709M+ subpages - About, Pricing, Products, Solutions, and more - delivered as cleaned Markdown text in structured JSON. Enables tracking of messaging changes, product updates, and competitive positioning over time.
## API
Base URL: `https://predictleads.com/api/v3`
Authentication requires an **API key** and an **API token**, available from your subscription page after signing up and verifying your email.
- Sign up: https://predictleads.com/sign_up
- Subscription & API credentials: https://predictleads.com/subscriptions
Three authentication methods are supported:
**HTTP Basic Auth** - `Authorization: Basic <base64("api_key:api_token")>`
**Request headers** - `X-Api-Key: YOUR_KEY` and `X-Api-Token: YOUR_TOKEN`
**Query parameters** - `?api_key=YOUR_KEY&api_token=YOUR_TOKEN`
Example request:
curl --request GET \
--url https://predictleads.com/api/v3/discover/news_events?category=product_launch \
--header 'X-Api-Key: {your_api_key}' --header 'X-Api-Token: {your_api_token}'
**Discovery endpoints** - filter across the full dataset by signal type, location, category, technology, company size, revenue, NAICS codes, and more:
- `GET /discover/companies` — Discover Companies
- `GET /discover/extended_companies` — Discover Extended Companies
- `GET /discover/job_openings` — Discover Job Openings
- `GET /discover/technologies/{technology_id_or_fuzzy_name}/technology_detections` — Discover Companies using a Technology
- `GET /discover/news_events` — Discover News Events
- `GET /discover/financing_events` — Discover Financing Events
- `GET /discover/portfolio_companies/connections` — Discover Portfolio Companies
- `GET /discover/public_companies/connections` — Discover Public Companies Connections
- `GET /discover/github_repositories` — Discover Github Repositories
- `GET /discover/products` — Discover Products
- `GET /discover/startup_platform_posts` — Discover Startup Platform Posts
**Company-specific endpoints** - fetch all signal types for a specific company by domain or ID:
- `POST /companies/{company_id_or_domain}/follow` — Follow the company
- `GET /companies/{id_or_domain}` — Get Company
- `GET /companies/{company_id_or_domain}/similar_companies` — Get Similar Companies
- `GET /companies/{company_id_or_domain}/job_openings` — Get Job Openings
- `GET /companies/{company_id_or_domain}/technology_detections` — Get Technology Detections
- `GET /companies/{company_id_or_domain}/news_events` — Get News Events
- `GET /companies/{company_id_or_domain}/financing_events` — Get Financing Events
- `GET /companies/{company_id_or_domain}/sec_filings` — Get SEC Filings
- `GET /companies/{company_id_or_domain}/connections` — Get Connections
- `GET /companies/{company_id_or_domain}/subpages` — Get Subpages
- `GET /companies/{company_id_or_domain}/github_repositories` — Get Github Repositories
- `GET /companies/{company_id_or_domain}/products` — Get Products
Credits are consumed per request on a monthly quota system.
**Rate limit**: 60 requests per second per API key. Returns HTTP 429 with a `Retry-After` header when exceeded. Space out requests when making bulk calls.
## Pricing
Pay-as-you-go, tiered billing - the more you use, the less you pay per credit. Billed monthly with a $40 minimum after the free tier.
- 1–100 credits: free
- 101–5,000 credits: $0.04 each
- 5,001–10,000 credits: $0.02 each
- 10,001–100,000 credits: $0.01 each
- 100,001–500,000 credits: $0.004 each
- 500,001+ credits: $0.002 each
Full pricing details: https://predictleads.com/pricing
## Delivery methods
- **REST API** - real-time access with JSON responses, authenticated by API key
- **Webhooks** - real-time updates on job openings, news events, technology detections, and key customers for followed companies
- **MCP (Model Context Protocol)** - native integration with Claude Desktop and MCP-aware clients for natural language queries against PredictLeads data. Endpoint: `https://mcp.predictleads.com/`
- **Flat Files** - bulk JSONL exports delivered via S3, GCS, or SFTP
## Integrations
Clay, Make.com, n8n, Active Pieces, Polytomic, Boost Space, Orthogonal, V7 Labs, Claude Desktop (MCP), Postman.
## Use cases
- **AI agents & agentic workflows** - power autonomous systems with live company signals via MCP or API
- **Sales enablement** - enrich CRMs, score accounts, personalize outreach with hiring and news signals
- **Market intelligence** - track industry trends, competitor moves, and market expansions
- **Investment research** - monitor hiring intent, funding activity, and company growth signals
- **Job board platforms** - power job aggregation and recruitment tools
- **Supply chain mapping** - reveal customer-vendor-investor relationships via connection data
## Pages
- [Homepage](https://predictleads.com/): Platform overview and dataset explorer
- [API Docs](https://docs.predictleads.com/): Full API reference with Swagger UI
- [Pricing](https://predictleads.com/pricing): Credit-based subscription plans
- [Integrations](https://predictleads.com/integrations): Integration marketplace
- [Alternatives](https://predictleads.com/alternatives): Comparisons with other company data providers
- [Data Use Cases](https://predictleads.com/data_use_cases): Industry and use case details
- [Case Studies](https://predictleads.com/case_studies): Customer stories
- [Blog](https://predictleads.com/blog/): Dataset guides, integration walkthroughs, case studies, and company news
