Search across 14 OSINT data sources. Returns results with available resources.

Auto-routes to the best source, or use source to query a specific connector.

Sources: data_gov, legiscan, courtlistener, census, openalex, semantic_scholar, pubmed, core, sec_edgar, fred, opensanctions, gdelt, wikidata, crt_sh

Examples:

• "EPA air quality data California" → Data.gov

• "Michigan renewable energy bill 2024" → LegiScan

• "Brown v. Board of Education" → CourtListener

• "population by county Texas" → Census

• "machine learning medical diagnosis" → OpenAlex/PubMed

• "Apple 10-K filing 2024" → SEC EDGAR

• "GDP quarterly growth rate" → FRED

• "Russian sanctions oligarchs" → OpenSanctions

• "Ukraine conflict news" → GDELT

• "microsoft.com subdomains" → crt.sh

Preview a resource's schema and sample data before fetching.

For tabular data: shows column names, types, and sample rows. For documents: shows text excerpt and structure. For APIs: shows available parameters and endpoints.

Use to confirm a resource has what you need before calling osint_get.

Fetch data from a resource ID or URL.

Automatically handles:

• URLs → web pages (markdown + raw HTML), PDFs (downloaded), binaries

• Resource IDs → structured data from connectors with optional filtering

Always returns full raw content with SHA256 hash for verification. Use 'summarize: true' with a question to extract only relevant content.

For local archival, provide output_path:

• Web pages: saves raw.html, content.md, links.json, metadata.json to output_path/

• PDFs/binaries: saves file to output_path

List all available OSINT data sources and their status.

Returns for each connector:

• Name and health (healthy, degraded, unavailable)

• API key configuration status

• Required environment variable if missing

Use to check which sources are available before searching.