Pod

Yes, this is on purpose. Pod is built for agents, so the default page is plain HTML.
Human? View the normal website.
Agent? You probably prefer /mcp/libofcongress-mcp-server/issues.md or /mcp/libofcongress-mcp-server/issues.json, or Pod over MCP.

Reported issues for libofcongress-mcp-server

Pod holds 21 of 40 problems reported by people outside the maintainer team. Issues filed by the project's own owners, members and collaborators are excluded entirely — a maintainer's release checklist is not a warning to a prospective user.

Back to libofcongress-mcp-server.

Most discussed

bug(loc_get_item,loc_get_newspaper_page): internal LOC API URL with query params leaked in not-found error messages

Not-found errors from libofcongress_get_item, libofcongress_get_newspaper_page, and the libofcongress://item/{item_id} resource expose the full internal LOC API URL — including query parameters like ?fo=json&at=item,resources,related_items — in data.url. The same leak occurs in serviceUnavailable errors when the LOC API returns an HTML body instead of JSON (rate-limited or maintenance page).

Steps to reproduce

  1. Call libofcongress_get_item with input: `{ "item_id": "TOTALLY_

Read the thread · 2026-05-24 · closed · 6 comments

bug(loc_get_item): format() truncates related_items at 5 without indicating truncation — parity gap with structuredContent

Server version

0.1.0

mcp-ts-core version

0.9.9

Runtime

Node.js

Runtime version

Node v25.9.0

Transport

HTTP (Streamable HTTP)

Description

libofcongress_get_item's format() caps both related_items and resource_links at 5 entries in content[]. Originally this was a silent drop (see comments below); a first fix added an "… and N more" overflow note to both blocks. Reopened: disclosure isn't the same as access. An overflow count tells a content[]-onl

Read the thread · 2026-05-24 · closed · 5 comments

bug(search_subjects): returns non-LCSH authority records

Server version

0.2.10

mcp-ts-core version

^0.10.9

Runtime

Bun

Runtime version

Bun 1.3.11

Transport

HTTP

Description

libofcongress_search_subjects is described as returning Library of Congress Subject Headings for use as the subject filter in libofcongress_search, but the live endpoint response includes name-authority and children-subject records ahead of real subject headings. That can send callers to labels that are not LCSH subject headings and may not

Read the thread · 2026-06-27 · closed · 3 comments

feat(get_item): expose research-critical metadata currently discarded

libofcongress_get_item describes itself as returning the full metadata record, but normalization drops several high-value fields already present in the requested item payload. The gap is most consequential for summaries, catalog identifiers, language/location context, and access restrictions.

Proposal

Expand the existing output with a curated set of research-critical fields rather than forwarding raw LOC JSON: summary, languages, locations, call_number, former_ids, `original_f

Read the thread · 2026-07-16 · closed · 2 comments

feat(search): add collection_slug to complete the browse-to-search workflow

libofcongress_browse_collections returns stable collection slugs, but no MCP tool can use them to search inside that collection. The design documentation already describes the slug as a libofcongress_search input, while the actual search schema has no collection/part-of filter.

Proposal

Add an optional collection_slug parameter to libofcongress_search. When present, route the existing query/filter/pagination shape through the corresponding collection endpoint so browse results becom

Read the thread · 2026-07-16 · closed · 2 comments

bug(item-resource): slash-separated item IDs cannot be read

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun 1.3.14

Transport

HTTP

Description

The libofcongress://item/{item_id} resource claims to return the same record as libofcongress_get_item, but it cannot address slash-separated item IDs returned by search. The tool succeeds for these IDs; the resource fails for both raw and percent-encoded URI forms.

Related: #24

Steps to reproduce

  1. Call libofcongress_get_item with `{ "item_id": "sn83025842/1

Read the thread · 2026-07-16 · closed · 2 comments

feat(error-handling): route rate-limit throws through ctx.fail() to engage contract-correlation machinery

The LocApiService throws rateLimited() factory errors directly from checkRateLimit() (line 130) and fetch() (line 157) in src/services/loc-api/loc-api-service.ts. All five tool handlers declare a rate_limit_exceeded error contract entry, but those throws originate inside the service layer — not via ctx.fail('rate_limit_exceeded', ...) in each handler's catch block. As a result, the framework's contract-correlation machinery is bypassed: data.reason is manually populated in the fa

Read the thread · 2026-05-29 · closed · 2 comments

bug(search): empty_results contract entry declared but never thrown on 4 search tools

Server version

0.2.5

mcp-ts-core version

^0.9.16

Runtime

Bun

Transport

stdio

Description

Four search tools declare an errors[] contract entry for empty_results with code JsonRpcErrorCode.NotFound, but none of them ever throw it. All four handlers return a structured success response with items: [] (or subjects: []) plus enrichment.notice carrying recovery guidance. The contract entry is dead code — data.reason is never 'empty_results', and `JsonRpcErr

Read the thread · 2026-05-29 · closed · 2 comments

Most recent

bug(errors): item_not_found and page_not_found reach the client with no recovery hint

Server version

0.2.16

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.x

Transport

HTTP

Description

The item_not_found and page_not_found contract entries declare useful recovery metadata, but neither throw site passes { recovery: { hint } }, so nothing reaches the wire. Both re-throw the service's message verbatim, and on a 404 that message is the generic notFound('LOC resource not found') raised inside fetchJson — it never names the

Read the thread · 2026-08-10 · open · 0 comments

feat(get_newspaper_page): request at=item,resource so newspaper_title, state, and edition stop coming back empty

Use case

libofcongress_get_newspaper_page declares newspaper_title, state, and edition in its output schema, and never populates any of them. The request asks LOC for ?fo=json&at=resource, and that projection returns exactly seven keys — fulltext_file, iiif_manifest_url, image, pdf, segment_count, url, word_coordinates. The title, date_issued, part_of, and sequence the handler reads are all null there, so state and edition are always absent and `part_of

Read the thread · 2026-08-10 · open · 0 comments

bug(search_subjects): count is the suggest endpoint's record tally, not the LOC item count it is described as

Server version

0.2.16

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.x

Transport

HTTP

Description

libofcongress_search_subjects describes count as "Approximate number of LOC items carrying this heading." It is parsed from the third array of the id.loc.gov /suggest/ OpenSearch response, which carries a per-suggestion description string — "1 result", "2 results" — counting matching authority records, not catalogued items. parseInt r

Read the thread · 2026-08-10 · open · 0 comments

bug(pagination): LOC 404s out-of-range pages, so recovery guidance is skipped and a valid collection_slug is reported missing

Server version

0.2.16

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.x

Transport

HTTP

Description

fetchSearchJson treats only HTTP 400 and 520 as "page out of range" (allowStatus: [400, 520] → null → the pages: 0 sentinel handlers key their recovery notice on). LOC actually answers a past-the-end page with 404 on every endpoint except /search/:

Endpoint Out-of-range status Result today
/search/ (no `f

Read the thread · 2026-08-10 · open · 0 comments

bug(get_item): object-form item.related_items violates the output schema and fails the call

Server version

0.2.16

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.x

Transport

HTTP

Description

libofcongress_get_item fails outright for any item whose item.related_items entries are objects rather than strings. RawLocItemResponse types the field as string[] and getItem spreads it straight into the normalized related_items: string[]:

relatedItems.push(...(item.related_items ?? []));

LOC returns objects (`{ title, url

Read the thread · 2026-08-10 · open · 0 comments

bug(tests): LOC_REQUEST_DELAY_MS override is a no-op, so the mocked suite sleeps ~137s

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.14

Transport

stdio

Description

bun run test takes ~137s. The same suite with LOC_REQUEST_DELAY_MS=0 in the environment takes ~975ms — a ~140x difference on a suite that mocks fetch and never reaches the network. The suite already tries to disable pacing per test, but the override never takes effect.

The cause is an ordering/caching interaction:

Read the thread · 2026-07-16 · closed · 1 comment

bug(browse_collections): returned slugs do not match LOC collection routes

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun 1.3.14

Transport

HTTP

Description

libofcongress_browse_collections describes slug as the identifier within loc.gov collection URLs, but the extractor only matches URLs ending immediately after /collections/<slug>/. Current LOC results end in /about-this-collection/, so the regex misses and fabricates a title-derived fallback that often is not a valid route.

Steps to reproduce

  1. Call `libofco

Read the thread · 2026-07-16 · closed · 1 comment

bug(search): advertised pagination extends past the LOC 100,000-result ceiling

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun 1.3.14

Transport

HTTP

Description

libofcongress_search computes pages and has_next from the full upstream total, but LOC stops serving deep pages after roughly 100,000 results. The tool therefore advertises page numbers that cannot be retrieved, then misclassifies the cap response as an ordinary out-of-range request.

Related: #4

Steps to reproduce

  1. Call libofcongress_search with `{ "query"

Read the thread · 2026-07-16 · closed · 1 comment

bug(browse_collections): discards upstream collection item counts

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun 1.3.14

Transport

HTTP

Description

libofcongress_browse_collections advertises collections[].item_count and says it returns collection item counts, but the service never populates the field even when the LOC collections response provides a top-level numeric count for every tested result.

Steps to reproduce

  1. Call libofcongress_browse_collections with { "limit": 2, "page": 1 }.
  2. Observe th

Read the thread · 2026-07-16 · closed · 1 comment

bug(response-parity): content and structuredContent diverge on success metadata

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun 1.3.14

Transport

HTTP

Description

Two success paths expose different facts depending on whether a client consumes structuredContent or content[].

  1. libofcongress_search always returns items[].is_item, but format() only emits a message when the value is false. For the live result sn83025842/1884-05-22/ed-1, structured clients see is_item: true; text-only clients receive no positive discrim

Read the thread · 2026-07-16 · closed · 1 comment

bug(loc-api-service): bare fetch has no retry or timeout, so transient network drops fail the tool call

Server version

0.2.12

mcp-ts-core version

0.10.14

Runtime

Bun

Runtime version

Bun 1.3.x

Transport

stdio

Description

LocApiService.fetch() calls global fetch() directly (src/services/loc-api/loc-api-service.ts:159), passing only ctx.signal. It uses neither withRetry nor fetchWithTimeout from @cyanheads/mcp-ts-core/utils — withRetry appears nowhere in src/. LcLinkedDataService has the same gap (`src/services/lc-linked-data/lc-linked-data-servi

Read the thread · 2026-07-15 · closed · 1 comment

feat(get_newspaper_page): derive basic metadata from page_url

libofcongress_get_newspaper_page returns full OCR text now, but date and sequence remain absent for normal URLs even though both values are already present in the required page_url.

Related: #17

Proposal

Derive low-risk metadata directly from the LOC newspaper page URL when the ?fo=json&at=resource endpoint omits it. For URLs like https://www.loc.gov/resource/sn82014248/1912-04-18/ed-1/?sp=12&q=titanic, the tool can return date: "1912-04-18" from the path and sequence: 12 f

Read the thread · 2026-06-27 · closed · 1 comment

bug(browse_collections): empty results report mismatched totalCount

Server version

0.2.10

mcp-ts-core version

^0.10.9

Runtime

Bun

Runtime version

Bun 1.3.11

Transport

HTTP

Description

libofcongress_browse_collections can return empty collections with total: 0 while enrichment reports totalCount: 1. The enrichment schema says totalCount mirrors output.total, so structured clients receive contradictory counts for the same response.

Steps to reproduce

  1. Call libofcongress_browse_collections with `{ "query": "z

Read the thread · 2026-06-27 · closed · 1 comment

The remaining reports are on the project's issue tracker.