libofcongress_search
Search LOC digital collections by keyword with optional format, date range, subject heading, geographic location, and collection filters. Returns item summaries with IDs for follow-up retrieval.
How to use it
libofcongress_search is exposed by the Libofcongress MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the libofcongress_search tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Libofcongress MCP Server
docker run --rm -p 3010:3010 libofcongress-mcp-serverOther tools in Libofcongress MCP Server (9)
scopes the search to one curated collection — pass a slug from libofcongressbrowsecollections. Mutually exclusive with format (each selects a different LOC endpoint); an unknown slug returns collectionnotfound
field indicates approximate number of LOC items carrying that heading (when available)
List and browse LOC curated digital collections with descriptions, item counts, and slugs. Optionally filter by keyword.
Retrieve full metadata for a specific LOC item — contributors, subjects, summary, languages, locations, rights, physical description, call number, formats, access restrictions, resource links (TIFF/JPEG/PDF), and related items.
Retrieve the full OCR text of a specific newspaper page. Pass the url field from a libofcongresssearchnewspapers result. Returns ocravailable: false when the page has no digitized text.
Search historical newspaper pages in the Chronicling America corpus. Returns pages with OCR text excerpts (~500 chars), publication title, date, state, and the URL needed for libofcongressgetnewspaperpage.
Search Library of Congress Subject Headings (LCSH) by keyword. Returns controlled-vocabulary labels and URIs — use the label as the subject filter in libofcongresssearch.
lists IDs of related LOC items for follow-up retrieval
contains URLs to downloadable digital files (TIFF, JPEG, PDF) for items with digital surrogates