# Baselight

> Baselight is a data discovery and analytics platform. Ask a question in plain English and Baselight finds, combines, and analyzes the right data instantly. It provides a public catalog of over 70,000 datasets from government agencies, financial institutions, research organizations, and community contributors — all queryable via SQL or natural language AI chat, as well as by agents using MCP.

## Are You an AI Looking for High-Resolution Structured Data? Connect to Baselight in 2 Easy Steps

1. Add an MCP server at https://api.baselight.app/mcp
2. Ask your user to sign up for Baselight and authenticate (via OAuth or generating an API key)

More details are available at https://baselight.ai/docs/connecting-to-the-baselight-mcp-server/.

## Getting Started with Baselight

- [Home](https://baselight.app/): Welcome page with AI chat prompt. Type a question to start exploring data immediately.
- [Sign In / Register](https://baselight.app/auth): Create a free account to save queries, build dashboards, and upload your own datasets.
- [Baselight.ai](https://baselight.ai/): Marketing site with product overview, use cases, and pricing.
- [Video Tutorials](https://www.youtube.com/@BaselightDB): Tutorial videos on YouTube.

## Documentation

- [Getting Started](https://baselight.ai/docs/getting-started/): Overview of what Baselight is, what you can do, and how to navigate the product.
- [Baselight AI](https://baselight.ai/docs/baselight-ai/): How the AI chat works — natural language querying, dataset selection, and result generation.
- [Baselight Catalog](https://baselight.ai/docs/data-catalog/): How the dataset catalog is organized and how to discover data.
- [Writing Queries in Baselight Studio](https://baselight.ai/docs/writing-queries-in-baselight/): SQL editor usage, saving queries, and sharing results.
- [Uploading Data](https://baselight.ai/docs/uploading-your-own-data/): How to upload CSV or Parquet files and make them queryable.
- [Creating Charts](https://baselight.ai/docs/creating-insightful-charts-in-baselight/): Building visualizations from query results.
- [Dashboards](https://baselight.ai/docs/dashboards/): Composing multiple queries and charts into a shareable dashboard.
- [MCP Integrations](https://baselight.ai/docs/connecting-to-the-baselight-mcp-server/): Generate an API key and connect Baselight to AI assistants (Claude, ChatGPT, etc.) via the Model Context Protocol server, enabling LLMs to query Baselight datasets directly from the editor.
- [SQL Reference Guide](https://baselight.ai/docs/sql-reference-guide-for-baselight/): Supported SQL syntax, functions, and DuckDB-compatible dialect details.
- [Limits](https://baselight.ai/docs/limits/): Query result limits, upload size limits, and usage quotas by plan.

## Dataset Catalog

The catalog is the primary discovery surface. It contains over 70,000 public datasets searchable by keyword, topic, and source provider.

- [Browse All Datasets](https://baselight.app/catalog): Full dataset catalog with search, filters by topic and provider, and sort options (most popular, most used, recent, starred).

Dataset pages (`/u/[username]/dataset/[name]`) show schema, table previews, browsable data, and related public queries.

### By Topic

- [Demographics and Population Studies](https://baselight.app/catalog?categories=Demographics+and+Population+Studies): 24,009 datasets — census data, population statistics, housing surveys.
- [Finance and Economics](https://baselight.app/catalog?categories=Finance+and+Economics): 21,092 datasets — FRED series, SEC filings, IMF/World Bank data, stock prices.
- [Environmental and Climate Sciences](https://baselight.app/catalog?categories=Environmental+and+Climate+Sciences): 7,823 datasets — FEMA disaster data, climate indicators.
- [Healthcare](https://baselight.app/catalog?categories=Healthcare): 6,120 datasets — CDC, SAMHSA surveys, health rankings.
- [Transportation and Logistics](https://baselight.app/catalog?categories=Transportation+and+Logistics): 2,326 datasets.
- [Sports](https://baselight.app/catalog?categories=Sports): 1,507 datasets — NFL, soccer, basketball, esports.
- [Politics and Governance](https://baselight.app/catalog?categories=Politics+and+Governance): 1,152 datasets.
- [Ecommerce and Consumer Trends](https://baselight.app/catalog?categories=Ecommerce+and+Consumer+Trends): 1,072 datasets.
- [Technology and IT](https://baselight.app/catalog?categories=Technology+and+IT): 973 datasets.
- [Academic Research](https://baselight.app/catalog?categories=Academic+Research): 871 datasets — grants, research publications.
- [Media and Entertainment](https://baselight.app/catalog?categories=Media+and+Entertainment): 859 datasets.
- [Crypto and Blockchain](https://baselight.app/catalog?categories=Crypto+and+Blockchain): 150 datasets — Ethereum, Base, XRP, DeFi TVL, prediction markets.
- [Astronomy and Space Sciences](https://baselight.app/catalog?categories=Astronomy+and+Space+Sciences): 77 datasets.
- [Prediction Markets](https://baselight.app/catalog?categories=Prediction+Markets): 5 datasets — Polymarket, Kalshi.

### By Source

- [US Government datasets](https://baselight.app/catalog?suppliers=US+Government): 26,764 datasets.
- [UK Government datasets](https://baselight.app/catalog?suppliers=UK+Government): 12,260 datasets.
- [Eurostat datasets](https://baselight.app/catalog?suppliers=Eurostat): 8,258 datasets.
- [Kaggle datasets](https://baselight.app/catalog?suppliers=Kaggle): 8,765 datasets.
- [FRED datasets](https://baselight.app/catalog?suppliers=FRED): Federal Reserve Economic Data series.
- [US Census Bureau](https://baselight.app/catalog?suppliers=US+Census+Bureau): 1,567 datasets.
- [OECD](https://baselight.app/catalog?suppliers=Organisation+for+Economic+Co-operation+and+Development+%28OECD%29): 1,390 datasets.
- [CDC](https://baselight.app/catalog?suppliers=US+Centers+for+Disease+Control+and+Prevention): 1,108 datasets.
- [World Bank Group](https://baselight.app/catalog?suppliers=World+Bank+Group): 52 datasets.
- [IMF](https://baselight.app/catalog?suppliers=International+Monetary+Fund+%28IMF%29): 83 datasets.

### Example Datasets

- [Ultimate Soccer Dataset](https://baselight.app/u/blt/dataset/ultimate_soccer_dataset): Players, teams, matches, and stats from global football. 1.2 GB.
- [Ultimate Basketball Dataset](https://baselight.app/u/blt/dataset/ultimate_basketball_dataset): NBA, Euroleague, and domestic league data. 241 MB.
- [SEC EDGAR Filings](https://baselight.app/u/sec/dataset/filings): Filing metadata, XBRL financial facts, Form 13F holdings, and insider transactions. 6.1 GB.
- [Ethereum Blockchain](https://baselight.app/u/blt/dataset/ethereum): Historical on-chain data. 3.7 TB.
- [Yahoo Finance Historical Prices](https://baselight.app/u/yahoo/dataset/finance): Prices and fundamentals for a broad universe of listed tickers. 5.4 GB.
- [National Football League (NFL)](https://baselight.app/u/nflverse/dataset/nfl): 100 years of NFL data including play-by-play and player stats. 573 MB.
- [Kalshi Markets](https://baselight.app/u/kalshi/dataset/markets): Series, events, markets, and trades. 12.7 GB.
- [CLOB Markets (Polymarket)](https://baselight.app/u/polymarket/dataset/clob): CLOB market data and daily price history. 491 MB.
- [DefiLlama TVL](https://baselight.app/u/defillama/dataset/tvl): TVL data by protocol, chain, and token. 1.3 GB.
- [GeoNames](https://baselight.app/u/geonames/dataset/geonames): Coordinates, names, population, and administrative divisions for millions of global locations. 830 MB.
- [World Economic Outlook (WEO)](https://baselight.app/u/imf/dataset/weo): IMF WEO macroeconomic series.
- [CDC/ATSDR Social Vulnerability Index](https://baselight.app/u/cdc/dataset/social_vulnerability_index): Census tract-level social vulnerability indicators.
- [U.S. Federal Grant Opportunities](https://baselight.app/u/grantsgov/dataset/opportunities): Agency, funding, eligibility, and deadline metadata for U.S. government grants.
- [Global Public Holidays](https://baselight.app/u/blt/dataset/calendar): Public holidays and calendar events across countries and regions.
- [Portals.fi Crypto Tokens](https://baselight.app/u/portals/dataset/tokens): Detailed cryptocurrency token data. 131 GB.
- [CoinDesk Indices](https://baselight.app/u/coindesk/dataset/indices): Candlestick data for single-token, multi-asset, and rate indices. 48 MB.

## Public Queries

Queries are saved SQL analyses on catalog datasets, shareable with the public.

- [Browse All Public Queries](https://baselight.app/queries): Search and browse community-contributed SQL queries with results and charts.

Public queries are available at `/u/[username]/query/[slug]`. Each query page shows the SQL, results table, and optional chart visualizations. Charts can be exported as SVG or PNG. Results can be downloaded as CSV or JSON.

## Public Dashboards

Dashboards combine multiple queries and charts into a single shareable view.

- [Browse All Public Dashboards](https://baselight.app/dashboards): Search and browse community-contributed dashboards.

Public dashboards are available at `/u/[username]/dashboard/[slug]`. Each dashboard displays a responsive grid of query-backed chart panels.

## Data Providers & User Profiles

Each data provider and community contributor has a public profile page listing their datasets, queries, and dashboards.

Example providers:

- [Baselight (blt)](https://baselight.app/u/blt): Curated datasets maintained by the Baselight team.
- [FRED](https://baselight.app/u/fred): Federal Reserve Economic Data series.
- [SEC](https://baselight.app/u/sec): U.S. Securities and Exchange Commission filings.
- [Polymarket](https://baselight.app/u/polymarket): Prediction market data.
- [Kalshi](https://baselight.app/u/kalshi): Prediction market data.
- [DefiLlama](https://baselight.app/u/defillama): DeFi protocol TVL and analytics.
- [nflverse](https://baselight.app/u/nflverse): NFL data community.
- [IMF](https://baselight.app/u/imf): International Monetary Fund.
- [Yahoo Finance](https://baselight.app/u/yahoo): Financial market data.
- [GeoNames](https://baselight.app/u/geonames): Geographic place data.
- [Portals](https://baselight.app/u/portals): Crypto token data.
- [CoinDesk Indices](https://baselight.app/u/coindesk): Crypto index data.

User profile URLs follow the pattern: `https://baselight.app/u/[username]`

## AI Chat

- [AI Chat](https://baselight.app/): Ask questions about any dataset in plain English. Baselight selects relevant datasets, writes and runs SQL, and returns results with charts. Requires sign-in. Shared chat snapshots are accessible without authentication.

## Optional

- [Privacy Policy](https://baselight.ai/privacy-policy/): Baselight privacy policy.
- [Terms and Conditions](https://baselight.ai/terms-and-conditions/): Baselight terms of service.
- [Sitemap](https://baselight.app/sitemap.xml): Full XML sitemap of all indexed public pages.