@cyanheads/smithsonian-mcp-server

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

Prerequisites

A free api.data.gov API key is required. Register at https://api.data.gov/signup — approval is instant. Set it as SMITHSONIAN_API_KEY in your MCP client config or .env file. The server will not start without it.

CC0 media gating: smithsonian_get_media only returns CC0-licensed (open access) images. Use smithsonian_search_objects with filters.cc0_only: true to find objects with downloadable media before calling it.

Related MCP server: swiss-cultural-heritage-mcp

Tools

Six tools covering the full Smithsonian Open Access workflow — filter vocabulary discovery, search, detail retrieval, CC0 image access, and cross-collection exploration:

smithsonian_search_objects

Full-text search with structured filters across the entire Smithsonian catalog.

• Free-text search over 14.5M objects from 20+ museums

• Filters: museum unit code, object type, indexed date term (1920s, 500-1500, 21st century, -2500), culture, geographic place, subject topic, named party (name), online-only, CC0-only

• topic and name are hard indexed constraints, not free text — topic: "Quilts" matches 1,134 objects where the bare word matches 2,677, and name: "Warhol, Andy" matches 421 against 715

• Returns curated summaries: title, date, museum, object type, thumbnail URL, CC0 flag, record_id

• Use start + rows for standard pagination (offset-based, max 100 per page)

smithsonian_list_terms

Enumerate the valid term vocabulary for an indexed filter field before applying filters.

• Supported fields: unit_code, culture, place, date, online_media_type, topic

• Returns the field's distinct term values as a page of the full vocabulary — no per-term object counts are available upstream

• Smithsonian uses a controlled vocabulary (terms are often plural, e.g. Paintings not Painting) — grounding filter values here avoids empty results

• Pass contains to filter the vocabulary by a case-insensitive substring — resolve a guessed value (e.g. greek → Greek, Attic) to its exact term(s) in one call, or confirm absence with an empty result

• For unit_code, a labels map returns each code's museum name and contains matches that name as well as the code, so National Air and Space resolves to NASM in one call

• Paginate with start + rows (default 50 per page, max 100); the largest vocabularies are topic (133k terms) and place (114k), so pair those with contains

• Each field's vocabulary is cached for SMITHSONIAN_TERMS_CACHE_TTL_SECONDS (default 1 hour) — upstream ignores paging and returns the whole set on every call, so paging a large vocabulary uncached re-downloads it each time

• object_type is not enumerable upstream — discover object-type values from the object_type field in smithsonian_search_objects results

smithsonian_get_object

Normalized catalog metadata for a single object.

• Input: record_id from smithsonian_search_objects — do not construct IDs manually

• Returns the exposed catalog fields: title, dates (all labeled), makers (with roles), materials, dimensions, place associations, culture terms, topic/subject terms, exhibition history, accession identifiers, credit line, rights statement

• Media summary included — call smithsonian_get_media for full image URLs

smithsonian_get_media

CC0-gated image access at multiple resolutions.

• Only CC0-licensed images are returned; throws Forbidden when an object has media but none is CC0

• Throws no_images when an object's media is entirely non-image (scanned books, 3D models, sound recordings); the recovery hint names the types present

• Each image entry includes thumbnail (~120px), screen-size (~800px), and high-resolution JPEG/TIFF URLs with pixel dimensions

• Use smithsonian_search_objects with filters.cc0_only: true before calling this tool

smithsonian_browse_category

Paginated browse within one exact category. For open-ended or topic discovery, use smithsonian_search_objects instead.

• Five modes: museum (by unit code, e.g. "NASM" — matched exactly, not by museum name), culture (e.g. "Aztecs"), period (indexed date term, e.g. "1940s" or "500-1500"), medium (object type, e.g. "Paintings"), topic (subject term, e.g. "Quilts")

• value must be an exact indexed category term — resolve museum, culture, period, and topic vocabulary with smithsonian_list_terms first; object_type is not enumerable there, so harvest it from smithsonian_search_objects results

• Returns total count, a page of sample objects, and a museum breakdown showing which institutions hold matching items (computed from the current page)

• Use start + rows for standard pagination (offset-based, start = page × rows, max 50 per page) — adjacent pages retrieve the objects a capped sample omits

• A category value that matches nothing throws invalid_category with a mode-specific recovery hint. A value outside the vocabulary gets the exact smithsonian_list_terms call that resolves it; a value the index enumerates but that matches no objects is named as such and routed elsewhere, since resolving it returns the same value

smithsonian_find_related

Cross-collection discovery via shared metadata signals.

• Matches the anchor's culture, named-party, topic, and period+type metadata signals against the wider catalog

• The named-party signal carries the catalog's own role for the party (maker, collector, donor, issuing authority, …) rather than a fixed maker label, prefers the indexed name facet as a hard filter when the record has one, and is dropped when its value only repeats the culture signal

• The topic signal is a hard topic: filter, so every object it tags carries that subject term rather than merely mentioning the word

• Surfaces related objects from across collections, each tagged with the metadata signals that connected it to the anchor

• Cross-museum discovery is the differentiator — an NASM aerospace anchor may surface related objects from NMNH, SAAM, and NMAH

• similarity_signals on each result show every metadata term that connected it to the anchor — an object surfaced by more than one signal carries all of them

• Page past a truncated result with start — a 0-indexed offset into the interleaved related set; page contiguously with start = page × limit (each signal is reachable to a depth of 5,000, fetched in ≤1,000-row chunks; a deeper page can shift an object by a bounded amount near a seam). A truncated response reports truncationCeiling as an upper bound on the reachable related pool

• signals[] breaks the fan-out down per signal: row_count is that signal's true upstream size (uncapped, so it can exceed the 5,000 reach) and search_continuation is the exact smithsonian_search_objects input that retrieves the signal's full match set at any depth — the retrieval path past this tool's per-signal reach

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool definitions — single file per tool, framework handles registration and validation

• Unified error handling — handlers throw, framework catches, classifies, and formats

• Pluggable auth: none, jwt, oauth

• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1

• Structured logging with optional OpenTelemetry tracing

• STDIO and Streamable HTTP transports

Smithsonian-specific:

• Wraps the Smithsonian Open Access API (14.5M objects across 20+ museums, 5.2M carrying CC0 media) with a free api.data.gov key

• CC0 gating on smithsonian_get_media — only open-access images returned, never restricted content

• Graceful degradation in smithsonian_find_related — a failure in one metadata signal doesn't abort the rest

• Response normalization across heterogeneous museum metadata schemas

Agent-friendly output:

• has_media on every object summary — agents can gate image download calls without an extra lookup (the is_cc0 flag is the metadata license, which the Open Access corpus carries almost everywhere)

• Typed error reasons (no_results, invalid_filter, not_found, no_media, no_images, not_cc0, invalid_id) with recovery hints for each case

• similarity_signals on related-object results let agents explain why objects were surfaced

• total_count on all search responses enables agents to communicate result scope before paginating

Getting started

Public Hosted Instance

A public instance is available at https://smithsonian.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "type": "streamable-http",
      "url": "https://smithsonian.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Requires a free api.data.gov API key — register at https://api.data.gov/signup and set SMITHSONIAN_API_KEY in your config.

Add the following to your MCP client configuration file:

{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/smithsonian-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "SMITHSONIAN_API_KEY": "your-api-key"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/smithsonian-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info",
        "SMITHSONIAN_API_KEY": "your-api-key"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "smithsonian-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "-e", "SMITHSONIAN_API_KEY=your-api-key",
        "ghcr.io/cyanheads/smithsonian-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 SMITHSONIAN_API_KEY=your-api-key bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+).

• A free api.data.gov API key — register at https://api.data.gov/signup. Approval is instant.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/smithsonian-mcp-server.git

2. Navigate into the directory:

cd smithsonian-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# Edit .env and set SMITHSONIAN_API_KEY

Configuration

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

Running the server

Local development

• 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 build -t smithsonian-mcp-server .
docker run --rm -e SMITHSONIAN_API_KEY=your-api-key -p 3010:3010 smithsonian-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/smithsonian-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md / AGENTS.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 via the barrel in src/mcp-server/tools/definitions/index.ts

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

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.