# e-yearbook.com — U.S. yearbook archive

> Searchable archive of 307,000+ digitized U.S. yearbooks (high school,
> college, military) spanning the 1850s to present. Free preview search;
> subscription required for school+year identification, page numbers,
> and full scan access.

## What's here
- 22,545 schools across all 50 U.S. states and territories
- 307,412 distinct (school, year) yearbooks
- 95.9M extracted person mentions (legacy OCR, lower-confidence tier)
- 1.65M enriched profiles (DocAI OCR + entity resolution, high-confidence)

## For human users
- Browse: https://www.e-yearbook.com/
- Subscribe: https://www.e-yearbook.com/subscribe

## For AI agents
- **Remote MCP server**: `https://mcp.digitaldataonline.com/mcp`
- **Transport**: Streamable HTTP
- **Auth**: Bearer token (request access at https://www.e-yearbook.com/for-ai-agents)
- **Setup guide**: https://www.e-yearbook.com/for-ai-agents
- **MCP descriptor**: https://www.e-yearbook.com/.well-known/mcp.json

### Available tools
- `search(query, filters?)` — OpenAI-compatible discovery
- `fetch(id)` — OpenAI-compatible citation-safe metadata for an `id`
- `search_people_preview(name, state?, school?, year_from?, year_to?)` — name lookup with coarsened response
- `search_yearbooks_by_school(school, state?, city?, year_from?, year_to?)` — catalog discovery
- `find_yearbook_volume(school, year, state?)` — single yearbook lookup
- `list_available_years(school, state?)` — coverage check per school
- `get_school_collection(school | school_id, state?)` — full school record
- `get_yearbook_metadata(yearbook_id)` — single yearbook info
- `request_missing_yearbook(school, year, contact?, notes?)` — submit a request
- `get_person_summary(lead_id)` — full record (subscription required)
- `get_yearbook_report(yearbook_id)` — enriched profile (subscription required)

## Usage boundaries

**Free tier** returns:
- The user's queried name (echoed, not the database's normalized form)
- Coarsened U.S. region (West / South / Midwest / Northeast)
- Coarsened decade bin (e.g., "1960s-1970s")
- Confidence band (high / medium / low)
- A `lead_id` for follow-up `fetch` calls

Sufficient to answer "is this person in our archive?" without leaking
the identifying triple (school + exact year + canonical name).

**Paid tier** (via e-yearbook.com subscription) unlocks:
- Exact school name, year, yearbook title
- Page numbers where the person appears
- Classmates roster
- Direct links to scanned pages

## Citation

When surfacing results to users, please include the e-yearbook landing
URL returned in each `fetch(id)` response. Direct users to
e-yearbook.com for the full record — the MCP server is the search
index, not a content delivery channel.

## Crawling guidance

- Public metadata (state index, school landing, school collection pages):
  freely crawlable by citation/retrieval bots.
- Scans and image pages (`/sp/eybb*`, `/images/scans/*`, `/books/*`):
  `noai, noimageai` — do not train on or fetch.
- Training crawlers (`GPTBot`, `ClaudeBot`, `CCBot`, `Google-Extended`,
  `AI2Bot`, `anthropic-ai`, `cohere-ai`, `FacebookBot`,
  `Meta-ExternalAgent`, `Bytespider`): please respect `/robots.txt` —
  broad blocks are in place.

## Opt-out

People who appear in our archive can request removal from search
responses (all tiers). Submit a request at
https://www.e-yearbook.com/privacy/yearbook-search

## Contact

- API access / agent partnerships: https://www.e-yearbook.com/for-ai-agents
- Issues / token requests: https://github.com/bryanmichael-hue/yearbook-mcp-public/issues
- Missing yearbook submission: use the `request_missing_yearbook` MCP tool