Bragproof

← Reports

@cyanheads/smithsonian-mcp-server

Starts with no setup0.4.1npm

Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.

Needs to start: nothing
Contacts while installing and starting: nothing

6tools listed
0hosts contacted
0files written
0.4 sto start
37dependencies

Its tool definitions changed since version 0.4.0. If you approved the earlier ones, read them again.

What it contacted

Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.

Starting it

npx -y @cyanheads/smithsonian-mcp-server@0.4.1

Installing a package runs its code. Use a sandbox for anything you have not read.

What its tools tell an agent

In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.

Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.

Tools

smithsonian_search_objects query, filters, rows, start
Recommended first step for open-ended or topic discovery: free-text search across 14.5 million Smithsonian objects, with optional exact filters. Filters narrow by museum unit, object type, indexed date term, culture, geographic place, subject topic, named party, scientific name, media type, online/CC0 availability, and objects on display now. Returns curated summaries (title, date, museum, thumbnail URL, CC0 flag) with the total match count. The record_id in each result is the identifier for smithsonian_get_object, smithsonian_find_related, and smithsonian_get_media. To browse one exact category — a single museum, culture, date term, object type, or topic — use smithsonian_browse_category instead.
smithsonian_list_terms field, start, rows, contains
Enumerate the valid term vocabulary for an indexed Smithsonian filter field (unit_code, culture, place, date, online_media_type, topic). Terms are a controlled vocabulary — often plural or qualified (e.g. "Paintings", not "Painting") — so guessed filter values tend to return nothing. Returns a page of the field's distinct term values; large vocabularies (topic has 133k terms, place 114k) page via start and rows. For unit_code, each code is returned with its museum name and contains matches the name as well as the code, so a museum name resolves to its code in one call.
smithsonian_get_object id
Fetch a normalized catalog metadata projection for a Smithsonian object by its record_id (from smithsonian_search_objects results). Returns title, dates, description, labeled notes, makers, materials, dimensions, places, cultures, topics, exhibition history, current display (on_view and current_exhibitions, for objects the catalog flags), credit line, identifiers, rights, and a media summary. indexed carries the exact name, place, object_type, date, and topic values the record is indexed under, each passable verbatim to the smithsonian_search_objects filter of the same name — the free-text makers, places, dates, and topics often differ from them. Natural-history records can include scientific_names, taxonomy, and collection coordinates without inferred precision. The media summary counts the media and links every non-image item (3D models, scanned books, documents); full image URLs come from smithsonian_get_media.
smithsonian_get_media id, start, limit
Return a Smithsonian object's CC0 (open-access) images at multiple resolutions, in catalog order, with cc0_image_count. An object with no CC0 image fails with its own reason: nothing digitized, media that is entirely non-image (3D models, scanned books, documents), or images that are all non-CC0. Page a long image list with start and limit: omit limit to get every image from start, and a start at or past cc0_image_count returns an empty images list. Each image includes a thumbnail (~150px), a screen-size image (~1,200px on the long edge), and a full-size JPEG — with pixel dimensions when the catalog lists a high-resolution JPEG — plus an archival TIFF when one exists. The cc0_only filter on smithsonian_search_objects surfaces objects that have downloadable CC0 images.
smithsonian_browse_category mode, value, rows, start
Browse Smithsonian objects within one exact category — a single museum (mode "museum"), culture, indexed date term (mode "period"), object type (mode "medium"), or subject term (mode "topic"). The value must be an exact indexed category term, not free text: resolve museum, culture, period, and topic vocabulary with smithsonian_list_terms first (object_type is not enumerable there — take the exact terms of a known object from smithsonian_get_object indexed.object_type, or harvest them from smithsonian_search_objects results, and treat each casing as its own category, since an object_type term covers only the casing it was written in). Returns the category total count, a page of matching objects, and a museum breakdown of that page; page the full category with start and rows. For open-ended or topic discovery, start with smithsonian_search_objects instead.
smithsonian_find_related id, limit, start, unit_code
Discover objects across Smithsonian collections related to a given anchor object, matched on shared metadata signals — culture, period, object type, named parties, and topic terms. Each related object is tagged with the signals that connected it to the anchor; a named-party signal carries the catalog's own role for that party (maker, Collector, Donor, issuing authority, …), not a fixed "maker" label. Matches surface across museums — an NASM aerospace anchor can pull related objects from NMNHPALEO, SAAM, and NMAH, and library and archive records that share a name or topic. Pass unit_code to keep every signal inside one museum.

Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.

Install facts

LicenseApache-2.0
Needsnode >=24.0.0
Sourcegithub.com/cyanheads/smithsonian-mcp-server
Install scriptsNone declared by it or anything installed with it.
Tarballsha512-BXsXFmhnL7I0CskP4O1Hkn8IjR5+W8OJoAYL0LVGHc1UP8OqPAa/d3loD9wVHlFFe8XuZIXe2CRrr8umPEGqEA==

Versions reported

VersionRunResultTools
0.4.12026-11-16Starts with no setup6
0.4.02026-11-12Starts with no setup6

Check this report yourself

This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.

Show it on your README

Bragproof: Starts with no setup

[![Bragproof](https://bragproof.smaverk.com/badge/@cyanheads/smithsonian-mcp-server.svg)](https://bragproof.smaverk.com/r/%40cyanheads/smithsonian-mcp-server)

New version out? Ask for a fresh report.