Enables searching and retrieving scanned pages from the Media History Digital Library, hosted on the Internet Archive, with full-text search and keyword-in-context excerpts.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@lantern-mcp search for 'Casablanca' in Variety from 1942"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A CLI and MCP server for Lantern, the full-text search platform of the Media History Digital Library — the digitised entertainment trade press. Variety, Billboard, the New York Clipper, Motion Picture Herald, Boxoffice, the studio year books and the fan magazines: roughly two million scanned pages of the industry writing about itself, from the 1900s to the 1960s.
No API key, no account, no registration.
Search resolves to an individual scanned leaf and returns that leaf's keyword-in-context excerpt inline, so judging a hit costs no second request. Every result links back to the page on the Internet Archive, with the search term pre-highlighted.
lantern search '"Gone with the Wind"' --from-year 1939 --to-year 1941 --per-page 3# "Gone with the Wind" [1939–1941] — 4475 results, page 1 of 1492
[1] December 1939 motionpictureher137unse
leaf 213 · Periodicals
... the première of {Gone} {with} {the} {Wind} in Atlanta ...
motionpictureher137unse_0213
http://archive.org/stream/motionpictureher137unse#page/n212/mode/2up/search/...Related MCP server: impresso-mcp
uv tool install --force --reinstall .That puts lantern on your PATH. To register the MCP server with Claude Code, Codex or Gemini:
uv run lantern-mcp-install # basic search tool only
uv run lantern-mcp-install --enable-advanced-search # plus filters and facetsThe CLI always exposes every filter; the MCP server hides the advanced ones behind that flag, because a tool schema sits in the model's context permanently whether it is used or not.
searchlantern search '"Technicolor"' # 86,314 results
lantern search '"Technicolor" AND Warner' # 33,868 results
lantern search '"Gone with the Wind"' --title Variety --sort date_asc
lantern search '"Gone with the Wind"' --collection 'Hollywood Studio System'Flag | Meaning |
| which result pages to fetch (default: 1) |
| results per request, up to 100 |
| year of publication, inclusive |
| exact collection value, e.g. |
| exact publication title, e.g. |
| exact format, e.g. |
| exact language, e.g. |
|
|
| emit JSON instead of text |
Every filter is optional and absent by default. The active ones are echoed back in the result header, so a small total is always traceable to what produced it.
A query is required. Lantern has no browse-everything mode: an empty query returns 0 results, and so does *, which is matched literally rather than as a wildcard. There is no filters-only search, so the CLI refuses one rather than returning a confident zero.
facetsThe filters match whole strings, so Vaudeville for Theatre and Vaudeville returns zero with no error — indistinguishable from an empty archive. facets is how you get the value verbatim:
lantern facets title '"Gone with the Wind"'# title values for "Gone with the Wind" — 21 listed
1331 Motion Picture Herald
1242 Boxoffice
1231 Variety
1014 Motion Picture Daily
686 The Exhibitor
523 Showmen's trade reviewThe counts describe that query's result set — which trade papers carry a term, and in what numbers. They are never corpus-wide: facet counts are computed over the hits, so a query is required here too. Without one every value comes back as 0, which reads as an empty archive rather than as the missing argument it is.
Fields: collection, title, format, language. There is no year, because year is a range filter rather than a list facet.
getlantern get motionpictureher137unse_0213Prints the path to the cached OCR text of that one leaf.
This is expensive per volume, not per page. Lantern indexes text it does not host: the scans live on the Internet Archive, which publishes OCR per volume and never per page. So reading one leaf means fetching that volume's OCR entire — 8 to 25 MB — and slicing the leaf out locally. The volume is then cached, so every later leaf of the same volume is free. Sweeping one publication is dramatically cheaper than sweeping across many.
Most of the time you do not need it: search already returns the excerpt.
The default operator is OR, not AND. This is the single most important thing to know about this source, and it fails silently:
lantern search 'Technicolor Warner' # 332,891 — pages holding EITHER word
lantern search '"Technicolor" AND Warner' # 33,868 — pages holding bothNothing in the first result set announces that it is mostly pages containing the word Warner. The CLI prints a warning when it sees two or more unquoted words for exactly this reason.
"quoted phrases" match exactly.
AND, OR and NOT all work. They partition cleanly: for one sample query, A AND B returned 788 and A NOT B returned 995, summing to the 1,783 of A alone.
Wildcards and proximity do not work and fail silently. A trailing * returns near-zero rather than expanding, and "a b"~2 breaks the phrase and degrades to OR, returning more results than the corpus has relevant pages.
Reported totals are true match counts, not a relevance-ranked tail: paging reaches exactly the reported total, and the last page holds the expected remainder. A total may therefore be quoted as a count, and --sort date_asc is safe on any query.
Facet counts are the exception: they sum to more than the total, because a volume can belong to several collections at once.
Lantern's robots.txt states crawl-delay: 5 for every user agent, and that is where this client's default pacing comes from — it is the site's published wish rather than a guess. Requests are spaced by a cross-process limiter, so several concurrent CLI invocations still share one budget.
Override with LANTERN_MIN_REQUEST_INTERVAL (seconds). Lowering it is asking for trouble on a free service that no one is being paid to run.
OCR downloads only — never search results. Under $XDG_CACHE_HOME/lantern-mcp, overridable with --cache-dir or LANTERN_CACHE_DIR. Volumes are cached whole and gzipped; individual leaves are written out beside them as plain text.
Apache 2.0.
Download one leaf's OCR text, returning the path to the cached file.
Use only when the search excerpt is not enough and the whole page has to be read or grepped. This is expensive per volume: the Internet Archive serves OCR per volume rather than per page, so the first leaf of a volume costs an 8-25 MB download and every later leaf of that volume is then free.
Inputs: reference (required). Returns: object
Search the entertainment trade press full text.
Lantern indexes the Media History Digital Library: Variety, Billboard, the New York Clipper, Motion Picture Herald, the studio year books and the fan magazines, roughly 1900-1960. This is the industry's own press - where stage acts were reviewed, booked and gossiped about by the trade that employed them - rather than general news coverage.
THE DEFAULT OPERATOR IS OR, NOT AND. Bare words are combined with OR, so
thought reader matches every page holding either word (272,059) while
"thought reader" matches the phrase (27). Always quote a phrase, or join
words with AND. Boolean AND, OR and NOT work; wildcards and proximity do not.
Each result resolves to one scanned leaf and carries its keyword-in-context excerpt inline, with matches in {braces}, so no further call is needed to judge a hit.
Inputs: query (required), page. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: one searches and returns excerpts, the other fetches full OCR text for a specific leaf. There is no ambiguity in their roles, and descriptions reinforce their complementary nature.
Both tool names follow a consistent verb_noun snake_case pattern: search_lantern and get_lantern_text. Even though one adds a modifier, the verb-first structure and shared domain noun keep the naming uniform and predictable.
With only two tools, the set feels minimal — at the low end of what's useful. For such a narrow domain (searching and reading a specific archive), two might suffice, but it still borders on overly thin.
The workflow is complete for the core use case: search to locate relevant pages, then fetch full text when needed. Minor gaps exist, such as no way to browse volumes or get metadata, but these are not essential for typical search-and-read tasks.
Chronicling America MCP — full-text search of ~150 years of digitized U.S. newspapers…
Search magazine articles and public previews, with publisher attribution and subscription links.
Search rights-cleared news and video from entitled publisher catalogs.
PLOS Search MCP — Solr-backed search over all PLOS journals.
