NARA Catalog

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/ianderso-nara-catalog-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Nov 1, 2026.

Tools

19 read · 1 write · 0 delete · 1 not yet classified

Secrets

1 (API keys, tokens or passwords)

Install scripts

None found

Runs as

Python package

Tools (21)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• aad_get_record

  Read one AAD row in full, with a citation in NARA's recommended form. Returns every field with its code's meaning, and the file, series and record group; the citation carries the date the row was retrieved. A NUMIDENT row gives parents' names and birthplace. It is still a transcription, not the record. Cite it as an electronic record, and get the original where one survives: the SS-5 from SSA, a manifest image.

• aad_list_series

  List the series in NARA's Access to Archival Databases (AAD), with each file's id. AAD holds name-searchable federal databases the Catalog tools cannot reach: the NUMIDENT (Social Security applications, claims and deaths, 1936-2007), WWII Army enlistments, ship passengers 1820-1912 and casualty files among them. aad_search works on one file at a time, and a big series is split into files: the NUMIDENT by entry type and surname range.

• aad_search

  Search one AAD file by `query` over the whole row and by `fields`. A wrong field name is refused with the file's search fields. A coded field (a state, a country) cannot be searched by field: put the meaning in `query`. Returns 50 rows a page, each with its record id. A row is a clerk's transcription or index entry, not the record: names are misspelt and dates wrong in it. No file holds everyone, so no hit is not proof of absence. Record ids change when NARA reloads a file; search again rather than reuse an old one.

• api_budget

  Report the key's Catalog API spend, this session and this month. A key is capped per month and a long sweep can exhaust it. Live calls are kept in a ledger beside the cache, so the month's figure survives restarts. Cached repeats cost nothing and are not counted.

• browse_children

  List a record's immediate children, one level down the hierarchy. The Catalog nests record group, then series, then file unit, then item. Searching finds a node; this walks down from it, which is how you get from a series you trust to the file unit for one person, and how you find out what else sits alongside a file you already have. A record's own ancestors come back from `get_record`.

• download_page_image

  Download one page of a record so it can actually be read. This is the step that turns a catalogue hit into evidence. The image is written to disk rather than returned inline — a page scan runs to several megabytes. NARA's media URLs are open and need no key, so this costs nothing against your API allowance. One catalogue call resolves the page list; the download itself is not an API call. A pension file can run to sixty pages and the page you need is rarely the first. Use get_extracted_text or get_transcriptions to find which page carries the fact, then fetch it by the object_id they name.

• get_comments

  Read other researchers' comments on a record. Comments often say what a file actually contains, where a related file sits, or that the description is wrong. None of it is verified by NARA: it is correspondence between researchers, useful for finding the next record and never a source in itself.

• get_extracted_text

  Read the OCR text NARA machine-extracted from a record's page images. This is a lead, not evidence. OCR was run over scans of handwriting, carbon copies and microfilm: it drops handwritten pages entirely, and it turns one surname into another silently. Use it to find which page matters, then open that page image with `get_record_images` and cite what you saw there -- never cite the OCR text itself. Returns one entry per digital object, in page order, with the text truncated to `max_chars`.

• get_online_availability

  List where else this record is available online. NARA records what has been digitised and published elsewhere, including by commercial partners. Use it to resolve a hint from a subscription site back to the archival original: the NAID and the reference unit are what make a citation refindable, and a partner's index entry is not a substitute for the page.

• get_partner_digital_objects

  List digital object ids a partner has matched to this record. NARA indexes metadata supplied by commercial partners — Ancestry among them — against its own records. A hit tells you the partner holds imagery for this NAID, which is worth knowing when NARA's own pages are not online. An empty list is the common answer and is not an error. It means no partner metadata has been matched, not that no partner holds the record. The ids are pointers into the partner's index, not a citation. Cite the archival record by NAID and reference unit.

• get_record

  Read one Catalog record in full, by NAID. Returns the scope and content note, the full hierarchy, the holding reference units, and every page-image URL. Use this once a search has given you a NAID worth pursuing.

• get_record_images

  List a record's page images in page order, each with its object id. These are the evidence. A catalog description summarises a file; it does not tell you what any individual page says, so read the images before citing anything to this record. The object id is what get_extracted_text and get_transcriptions entries point at; pass it, or the page number, to download_page_image.

• get_tags

  Read the citizen tags on a record. On genealogical records tags are very often the names of the people who appear inside the file -- the widow, the children, the witnesses -- which the title does not carry. A tag is a stranger's reading of the document and is not evidence: follow it to the page image and cite what the image shows.

• get_transcriptions

  Read the citizen transcriptions of a record's pages. Volunteers have transcribed handwritten pension files, service records and letters that OCR cannot touch, which makes this the fastest way into a document in copperplate. It is still a lead, not evidence: a transcription is one stranger's reading, unreviewed, and names are exactly where such a reading goes wrong. Check the page image before citing a name or date you found here, and cite the image. Returns one entry per transcription with its text, its author and the page it belongs to.

• search_by_contribution_text

  Search what people wrote on records, and get the records back. This is the difference between searching a catalogue and searching the documents. A pension file titled only with the veteran's name will name his widow, his children and his witnesses in its transcribed text — none of which a title search reaches. Unlike `search_transcriptions` and its siblings, which return the contributions themselves, this filters the main index and returns full record summaries. Use this when you want the record; use those when you want to read what a particular volunteer wrote. A transcription is one volun…

Signals

Stars

0

Forks

0

Open issues

0

Weekly downloads

51

Last commit

Oct 6, 2026 (27 days ago)

Last release

Oct 6, 2026 (27 days ago)

Last package publish

Oct 6, 2026 (27 days ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.ianderso/nara-catalog-mcp

Version

1.1.0

Auth

API key

Packages

pypi nara-catalog-mcp

License

MIT

Repository

github.com/ianderso/nara-catalog-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql