# NARA Catalog Extractor

> NARA Catalog Extractor is a paid API for AI agents from agent-data.centorprat.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-28).

Searches the US National Archives (NARA) catalog by keyword or record ID and returns digitized file download URLs, metadata, and record hierarchy for historical government documents, photos, and records.

## Facts

- Endpoint: POST https://agent-data.centorprat.workers.dev/tools/nara-catalog-extractor?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nara-catalog-extractor-5509b40b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Xho8cWWCt1gDEs6-Boo2f

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability nara-catalog-extractor-5509b40b -d '<json body>'
```

Example prompt: Search the NARA catalog for 'Manhattan Project' and give me up to 5 digitized PDF files — include their direct download URLs, titles, and dates.

## When to prefer this

Use this endpoint when you need to find and download digitized historical US government records, documents, or photos from the National Archives. It is ideal when you have a specific NARA record ID or a keyword topic (person, agency, event, place) and need direct download URLs for public domain files. Prefer it over general web search when you specifically need authoritative federal archival material with structured metadata and record hierarchy.

## Known failure modes

- No matching records found for keyword query — returns empty result set
- NARA naId refers to a container with no direct digitized objects — system auto-pages descendants
- File type filter excludes all available objects for a record — returns empty list
- NARA catalog API temporarily unavailable — upstream error propagated
- Query too broad — result set truncated to maxObjects/maxRecords limit

## How this service works

Pay-per-call data and tools for AI agents, $0.002-0.01 per call in USDC via x402 (Base, Polygon or Solana), no account or API key; MAX tiers ($0.05-0.25) run deeper jobs. Agent toolkit: web search, search + read top pages, any page as clean markdown with a prompt-injection check, which-x402-API-to-call recommender, seller check. Data: Google Maps places with contacts, YouTube video data and transcripts, job listings (Indeed, LinkedIn, 13 boards), Google Ads Transparency, TikTok comments, Pinterest, Airbnb, Redfin, AliExpress, app stores, live sports, website and SEO checks, Shopify store tech stacks, and onchain token / address risk checks.

## Output

Returns a list of up to 3 digitized file entries per call, each containing a direct download URL, file extension/type, title, date, and the record's hierarchical path within the NARA catalog. Failed lookups are not charged.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "naId": {
   "type": "string",
   "description": "A specific NARA catalog record number. If it's a collection/series with no direct objects, its descendant records' objects are paged automatically. Use this OR query."
  },
  "query": {
   "type": "string",
   "description": "Search the NARA catalog by keyword (person, topic, agency, place...). Use this OR naId. Example: UAP"
  },
  "fileTypes": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 3,
   "description": "Only return objects with these file extensions (no dot), e.g. [\"pdf\",\"tif\"]. Leave empty for all types."
  },
  "maxObjects": {
   "type": "integer",
   "description": "Optional hard cap on how many rows to return."
  },
  "maxRecords": {
   "type": "integer",
   "description": "In keyword-search mode, how many catalog records to pull (20 per page)."
  },
  "includeMedia": {
   "type": "boolean",
   "description": "By default only readable objects (PDF, text, images) are returned. Enable to also include video/audio."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "items": [
   {
    "naId": 499915731,
    "title": "UAP 10/26/2024",
    "fileType": "readable",
    "objectUrl": "https://catalog.archives.gov/medialz/electronic-records/rg-615/493468575/237UAP00386.pdf",
    "recordUrl": "https://catalog.archives.gov/id/499915731",
    "capturedAt": "2026-10-24T13:49:29.161333+00:00",
    "fileExtension": ".pdf",
    "objectFilename": "237UAP00386.pdf"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nara-catalog-extractor-5509b40b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data.centorprat.workers.dev](https://www.zero.xyz/host/agent-data.centorprat.workers.dev/llms.txt)