Skip to main content
Glama
@cyanheads/libofcongress-mcp-server

@cyanheads/libofcongress-mcp-server

by cyanheads

Version License Docker MCP SDK npm TypeScript Bun

Install in Claude Desktop Install in Cursor Install in VS Code

Framework

Public Hosted Server: https://libofcongress.caseyjhand.com/mcp


Overview

Library of Congress digital collections, Chronicling America historic newspapers, and LC Subject Headings. Search items and newspaper pages, read full metadata and OCR text, resolve subject terms, and browse curated collections.

Tools

Tool

Description

libofcongress_search_items

Search LOC digital collections by keyword with format, date range, subject, location, contributor, and collection filters.

libofcongress_get_item

Retrieve full metadata for a specific LOC digital item — imprint, contributors, subjects, rights, formats, its digital resources, and a paged list of its pages.

libofcongress_search_newspapers

Search historical newspaper pages in the Chronicling America corpus, with an excerpt of each page's opening OCR text.

libofcongress_get_newspaper_page

Retrieve the full text and metadata of one page — a newspaper page, or a book or manuscript page from libofcongress_get_item — or only the passages around a search term.

libofcongress_search_subjects

Search Library of Congress Subject Headings (LCSH) by keyword.

libofcongress_browse_collections

List and browse LOC curated digital collections, optionally filtered by keyword.

Resources

Resource

Description

libofcongress://item/{+item_id}

LOC digital item metadata by ID — stable URI for injecting item context into agent conversations.

All resource data is also reachable via libofcongress_get_item. Use libofcongress_search_items to discover item IDs first.

Research guide

libofcongress-guide covers identifier chains, OCR uncertainty, research coverage, and collection, newspaper, book, and manuscript workflows. It ships with plugin, npm, Docker, and MCPB installs and is also available through MCP skill discovery and resource reads.

Related MCP server: historical-investigator-mcp

Capability reference

libofcongress_search_items tool

  • Filters: eight material formats (photo, map, newspaper, manuscript, audio, film, book, notated-music), inclusive year range (date_start/date_end), subject (an LCSH heading from libofcongress_search_subjects or a facet term), location, contributor (a name as LOC indexes it, without dates or roles), and collection_slug (from libofcongress_browse_collections, combinable with format); up to 100 results per page — a larger limit (up to 1000) is served as 100 with effectiveLimit and a notice

  • Use query: "*" to browse without a keyword. sort accepts relevance (default), date (oldest first), or date_desc (newest first); effectiveSort echoes the order LOC applies before pagination

  • Each result carries date as LOC catalogs it and is_item: true for catalog items whose id resolves via libofcongress_get_item, false for other resources. Newspaper rows include page_url for libofcongress_get_newspaper_page; retired catalog links carry link_notice and retain their original URL. Other non-item rows can be opened at url. contributor_terms lists the contributors LOC credits a row with, in the form the contributor filter accepts

  • include_facets: true adds subject_facets, location_facets, and contributor_facets (LOC's top 10 terms across all matches, each with its item count); off by default since it slows every search. A zero-result notice names the subject terms, location, and contributor applied

  • A subject, location, or contributor value with | inside it is rejected as invalid_filter_value (a | at either end is dropped); a query LOC refuses as too long fails as query_too_long


libofcongress_get_item tool

  • Takes a search result's id (simple or multi-segment, e.g. sn95047246/1935-09-05/ed-1), a loc.gov item link, or an lccn.loc.gov permalink; any other URL is rejected as invalid_item_id before any request

  • Returns the imprint, contributors with roles and contributor_terms (the names the search contributor filter accepts), LCSH subject_headings, subject_terms (the lowercase terms the search subject filter accepts), notes, summary, languages, locations, rights_information as plain text, physical description, call number, former IDs, formats, and access_restricted; fields absent upstream are omitted

  • resources lists every digital resource with its page count, image, pdf, audio (MP3), video (MP4), and download_restricted; a recording, tape side, or film reel LOC sends with only its media file has no url and no pages. has_transcription marks a resource whose document has one transcription, which libofcongress_get_newspaper_page returns for any of its pages. pages lists 50 pages at a time by default (page_offset, page_limit, page_total, next_page_offset; at most 100 per call — a larger page_limit, up to 1000, is served as 100 with effectivePageLimit and a notice), each with a page_url and has_text that read through libofcongress_get_newspaper_page. include_files: true adds each page's download URLs


libofcongress_search_newspapers tool

  • Filters: keyword, inclusive date range down to the day (date_start/date_end take an integer year or a YYYY, YYYY-MM, or YYYY-MM-DD string), indexed state/province (full name or supported US postal code), newspaper title (the exact newspaper_title of a search result), and language (as LOC indexes it, e.g. german; a bilingual page matches each of its languages); up to 100 results per page — a larger limit (up to 1000) is served as 100 with effectiveLimit and a notice

  • sort accepts relevance (default), date (oldest first), or date_desc (newest first); effectiveSort echoes the applied order

  • Each result carries the opening ~500 characters of the page's OCR text, states, languages, and the url that libofcongress_get_newspaper_page takes verbatim

  • include_facets: true adds newspaper_title_facets, state_facets, and language_facets (LOC's top 10 values across all matches, each with LOC's page count), the values the newspaper_title, state, and language filters accept unchanged; off by default since LOC's facet block is large. A | inside a filter value is rejected as invalid_filter_value (one at either end is dropped); a query LOC refuses as too long fails as query_too_long

  • The excerpt is the page's first lines, not the text around the match; pass the same query as match to libofcongress_get_newspaper_page for the passages around it


libofcongress_get_newspaper_page tool

  • Takes the url from a libofcongress_search_newspapers result, or a pages[].page_url from libofcongress_get_item (newspaper, book, and manuscript pages alike), plus Chronicling America page links; a link that names no single page, any other host, or a malformed path or sp is rejected as invalid_page_url before any request

  • Returns the page's text as ocr_text with newspaper_title, date, place_of_publication, states, edition, sequence, segment_count, item_title, and item_id (pass it to libofcongress_get_item to list the item's pages). ocr_available: false marks an image-only page, and a notice explains an empty result: the text service did not answer (retry), the body could not be read as text, or the page is blank

  • A manuscript or printed pamphlet LOC transcribed as one document (the Lincoln papers, for one) returns that whole transcription as ocr_text on any of its pages, text_scope: "document", with text_attribution when LOC names a transcriber; a page with a text service of its own is text_scope: "page". A manuscript's transcription omits the editors' notes and the wording the writer canceled

  • match returns only the passages around a term — pass the query you searched with. Space-separated words are separate terms and a double-quoted span is one phrase, matched case-insensitively. matches holds up to 10 passages of about 300 characters either side of each occurrence, match_count counts every occurrence, and ocr_text is empty; a notice says when nothing matched or some occurrences fall outside the passages. If text retrieval fails, both match fields are absent because the result is unknown; blank and image-only pages still report zero


libofcongress_search_subjects tool

  • Keyword query, up to 250 results per call (default 10; a larger limit, up to 1000, returns up to 250 with a notice); returns the authorized LCSH label and stable LOC uri

  • Start at offset: 0 (default), then pass next_offset to continue. total counts this page's headings; the final or past-end page omits next_offset. A past-end offset succeeds empty with a recovery notice

  • An exact match from the first 50 results moves to the start. Subsequent offsets and changed limits preserve that ordering while the upstream results remain unchanged

  • Pass the label verbatim as libofcongress_search_items's subject filter. A partial word (aerial photog) falls back to headings that begin with it


libofcongress_browse_collections tool

  • Optional keyword filter on collection name and description; up to 100 collections per page — a larger limit (up to 1000) is served as a 100-collection page with effectiveLimit and a notice

  • Each collection carries a slug for libofcongress_search_items's collection_slug (taken from the loc.gov route, not derivable from the title); item_count is approximate and omitted when LOC doesn't provide it

  • A keyword LOC refuses as too long fails as query_too_long


libofcongress://item/{+item_id} resource

  • Returns the same record as libofcongress_get_item, as application/json, with the first 50 pages and no files; next_page_offset marks where libofcongress_get_item's page_offset continues

  • item_id comes from a libofcongress_search_items result's id; anything that is not an item ID is rejected as invalid_item_id. Multi-segment newspaper IDs keep their slashes (libofcongress://item/sn95047246/1935-09-05/ed-1)

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

Library of Congress-specific:

  • Request queue in front of www.loc.gov: calls start in arrival order, at least LOC_REQUEST_DELAY_MS apart (default 3100ms, ~19 req/min), never exceeding LOC's 20 per minute. A call that cannot start in time fails as server_busy with retryAfter

  • Rate-limit handling: a 429 triggers LOC's 1-hour block, and calls fail without sending anything until it lifts (never retried); a Cloudflare challenge or HTML page instead of JSON fails as upstream_unavailable with retryAfter: 60. libofcongress_search_subjects (id.loc.gov) is unaffected

  • A 50-second budget per tool call covers queue wait, retries, and the OCR or transcription fetch, so a slow upstream fails as request_timed_out, which on the www.loc.gov tools is retryable with a recovery that leads with one unchanged retry; other upstream failures (dropped connections, any other error status, empty or truncated bodies) fail as upstream_unavailable with a retry hint

  • Pages past the end of the results or past the retrieval ceiling return an empty result with a notice, not an error

  • Newspaper OCR is surfaced as-is; 19th-century or degraded pages may contain garbled text

Agent-friendly output:

  • Empty results include a notice with recovery hints that echo the applied filters

  • Item and newspaper searches carry pagination status (total, page, pages, has_next), capped at LOC's ~100,000-item retrieval ceiling; subject searches use offset and next_offset with a page-local total

  • ocr_available and is_item let callers branch without parsing text

  • Every typed error carries a recovery hint

Getting started

Connect Claude Code to the hosted server:

claude mcp add --transport http libofcongress-mcp-server https://libofcongress.caseyjhand.com/mcp

Or run it locally:

claude mcp add libofcongress-mcp-server -- npx -y @cyanheads/libofcongress-mcp-server

For other clients, add this to the MCP config file:

{
  "mcpServers": {
    "libofcongress-mcp-server": {
      "command": "npx",
      "args": ["-y", "@cyanheads/libofcongress-mcp-server"]
    }
  }
}

No API key is required. Set LOC_USER_AGENT to identify your application to LOC. For Docker or a source build, see Running the server.

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts.

Variable

Description

Default

LOC_USER_AGENT

User-Agent header sent with LOC API requests. LOC recommends a descriptive value for polite access.

libofcongress-mcp-server/0.6.1

LOC_REQUEST_DELAY_MS

Delay in milliseconds between LOC API requests to stay under the 20 req/min rate limit.

3100

MCP_TRANSPORT_TYPE

Transport: stdio or http.

stdio

MCP_HTTP_PORT

Port for HTTP server.

3010

MCP_AUTH_MODE

Auth mode: none, jwt, or oauth.

none

MCP_SESSION_MODE

HTTP session mode. This server is explicitly stateless.

stateless

MCP_LOG_LEVEL

Log level (RFC 5424).

info

LOGS_DIR

Directory for log files (Node.js only).

<project-root>/logs

LOG_TOOL_FAILURE_PAYLOADS

Log each failed tool call's arguments and result, redacted by key name and capped at LOG_TOOL_FAILURE_PAYLOAD_MAX_BYTES (default 16384). A secret inside a free-form value is not redacted.

false

STORAGE_PROVIDER_TYPE

Storage backend.

in-memory

OTEL_ENABLED

Enable OpenTelemetry instrumentation (spans, metrics, completion logs).

false

See .env.example for the full list of optional overrides.

Running the server

Local development

Requires Bun v1.4.4 or higher (or Node.js v24+).

git clone https://github.com/cyanheads/libofcongress-mcp-server.git
cd libofcongress-mcp-server && bun install
cp .env.example .env
# Optionally set LOC_USER_AGENT or LOC_REQUEST_DELAY_MS.
  • Build and run:

    # One-time build
    bun run rebuild
    
    # Run the built server
    bun run start:stdio
    # or
    bun run start:http
  • Run checks and tests:

    bun run devcheck   # Lint, format, typecheck, security
    bun run test       # Vitest test suite
    bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker run --rm -p 3010:3010 ghcr.io/cyanheads/libofcongress-mcp-server:latest

The image defaults to HTTP transport, stateless session mode, and logs to /var/log/libofcongress-mcp-server. For stdio in an MCP client, use "command": "docker" with "args": ["run", "-i", "--rm", "-e", "MCP_TRANSPORT_TYPE=stdio", "ghcr.io/cyanheads/libofcongress-mcp-server:latest"]. Build locally with docker build -t libofcongress-mcp-server .; OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Directory

Purpose

src/index.ts

createApp() entry point — registers tools, resource, and initializes services.

src/config

Server-specific environment variable parsing (LOC_USER_AGENT, LOC_REQUEST_DELAY_MS).

src/mcp-server/tools

Tool definitions (*.tool.ts) — six LOC tools.

src/mcp-server/resources

Resource definitions — libofcongress://item/{+item_id}.

src/services/loc-api

LocApiService wrapping www.loc.gov — search, item fetch, page text, collection browser.

src/services/lc-linked-data

LcLinkedDataService wrapping id.loc.gov — LCSH subject heading suggest.

tests/

Unit and integration tests mirroring src/.

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

  • Handlers throw, framework catches — no try/catch in tool logic

  • Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

  • Register new tools and resources via the arrays in src/index.ts

  • Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      MCP server for searching and retrieving full-text pages from the Library of Congress, including newspapers, books, and manuscripts, via the loc.gov API.
      3
      Apache 2.0
    • A
      license
      A
      quality
      B
      maintenance
      An MCP server for the Library of Congress that enables searching scanned American newspaper pages, searching catalogue items by media type, reading individual records, and listing digital collections, all without requiring an API key or account.
      4
      211 npm
      MIT