Search 14.5M Smithsonian Open Access objects across 20+ museums via MCP, and retrieve CC0 images for the 5.2M that carry openly-licensed media. STDIO or Streamable HTTP.\n
\n\n[](https://github.com/cyanheads/smithsonian-mcp-server/releases/latest/download/smithsonian-mcp-server.mcpb) [](https://cursor.com/en/install-mcp?name=smithsonian-mcp-server&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBjeWFuaGVhZHMvc21pdGhzb25pYW4tbWNwLXNlcnZlciJdLCJlbnYiOnsiTUNQX1RSQU5TUE9SVF9UWVBFIjoic3RkaW8iLCJTTUlUSFNPTklBTl9BUElfS0VZIjoieW91ci1hcGkta2V5In19) [](https://vscode.dev/redirect?url=vscode:mcp/install?%7B%22name%22%3A%22smithsonian-mcp-server%22%2C%22command%22%3A%22npx%22%2C%22args%22%3A%5B%22-y%22%2C%22%40cyanheads%2Fsmithsonian-mcp-server%22%5D%2C%22env%22%3A%7B%22MCP_TRANSPORT_TYPE%22%3A%22stdio%22%2C%22SMITHSONIAN_API_KEY%22%3A%22your-api-key%22%7D%7D)\n\n[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)\n\n
\n\n---\n\n## Prerequisites\n\n> **A free `api.data.gov` API key is required.** Register at [https://api.data.gov/signup](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.\n>\n> **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.\n\n---\n\n## Tools\n\nSix tools covering the full Smithsonian Open Access workflow — filter vocabulary discovery, search, detail retrieval, CC0 image access, and cross-collection exploration:\n\n| Tool | Description |\n|:---|:---|\n| `smithsonian_search_objects` | Search across 14.5M objects by text query with optional filters (museum, type, date term, culture, place, topic, name, online-only, CC0). Returns curated summaries with total count. |\n| `smithsonian_list_terms` | Enumerate the valid term vocabulary for an indexed filter field (unit_code, culture, place, date, online_media_type, topic). Call before filtering to avoid empty results from invalid values; pass `contains` to resolve a guessed value to its exact term(s). `unit_code` terms come back with their museum names. |\n| `smithsonian_get_object` | Fetch a normalized catalog metadata projection for an object by ID: title, dates, materials, dimensions, exhibition history, credit line, and identifiers. |\n| `smithsonian_get_media` | Return all CC0-licensed images for an object at multiple resolutions (thumbnail, screen, high-res JPEG/TIFF). Only CC0 images returned, never an empty list — a distinct error reason names why, whether the object has nothing digitized, only non-image media, or only restricted images. |\n| `smithsonian_browse_category` | Browse objects within one exact category (museum, culture, period, medium, topic) with total count, a page of objects, and museum breakdown. Requires an exact indexed category term. |\n| `smithsonian_find_related` | Discover cross-collection objects related to an anchor, matched on shared culture, named-party, topic, and period signals. |\n\n### `smithsonian_search_objects`\n\nFull-text search with structured filters across the entire Smithsonian catalog.\n\n- Free-text search over 14.5M objects from 20+ museums\n- 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\n- `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\n- Returns curated summaries: title, date, museum, object type, thumbnail URL, CC0 flag, `record_id`\n- Use `start` + `rows` for standard pagination (offset-based, max 100 per page)\n\n---\n\n### `smithsonian_list_terms`\n\nEnumerate the valid term vocabulary for an indexed filter field before applying filters.\n\n- Supported fields: `unit_code`, `culture`, `place`, `date`, `online_media_type`, `topic`\n- Returns the field's distinct term values as a page of the full vocabulary — no per-term object counts are available upstream\n- Smithsonian uses a controlled vocabulary (terms are often plural, e.g. `Paintings` not `Painting`) — grounding filter values here avoids empty results\n- 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\n- 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\n- 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`\n- 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\n- `object_type` is not enumerable upstream — discover object-type values from the `object_type` field in `smithsonian_search_objects` results\n\n---\n\n### `smithsonian_get_object`\n\nNormalized catalog metadata for a single object.\n\n- Input: `record_id` from `smithsonian_search_objects` — do not construct IDs manually\n- 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\n- Media summary included — call `smithsonian_get_media` for full image URLs\n\n---\n\n### `smithsonian_get_media`\n\nCC0-gated image access at multiple resolutions.\n\n- Only CC0-licensed images are returned; throws `Forbidden` when an object has media but none is CC0\n- 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\n- Each image entry includes thumbnail (~120px), screen-size (~800px), and high-resolution JPEG/TIFF URLs with pixel dimensions\n- Use `smithsonian_search_objects` with `filters.cc0_only: true` before calling this tool\n\n---\n\n### `smithsonian_browse_category`\n\nPaginated browse within one exact category. For open-ended or topic discovery, use `smithsonian_search_objects` instead.\n\n- 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\"`)\n- `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\n- Returns total count, a page of sample objects, and a museum breakdown showing which institutions hold matching items (computed from the current page)\n- Use `start` + `rows` for standard pagination (offset-based, `start = page × rows`, max 50 per page) — adjacent pages retrieve the objects a capped sample omits\n- 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\n\n---\n\n### `smithsonian_find_related`\n\nCross-collection discovery via shared metadata signals.\n\n- Matches the anchor's culture, named-party, topic, and period+type metadata signals against the wider catalog\n- 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\n- The topic signal is a hard `topic:` filter, so every object it tags carries that subject term rather than merely mentioning the word\n- Surfaces related objects from across collections, each tagged with the metadata signals that connected it to the anchor\n- Cross-museum discovery is the differentiator — an NASM aerospace anchor may surface related objects from NMNH, SAAM, and NMAH\n- `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\n- 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\n- `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\n\n---\n\n## Features\n\nBuilt on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@cyanheads/mcp-ts-core):\n\n- Declarative tool definitions — single file per tool, framework handles registration and validation\n- Unified error handling — handlers throw, framework catches, classifies, and formats\n- Pluggable auth: `none`, `jwt`, `oauth`\n- Swappable storage backends: `in-memory`, `filesystem`, `Supabase`, `Cloudflare KV/R2/D1`\n- Structured logging with optional OpenTelemetry tracing\n- STDIO and Streamable HTTP transports\n\nSmithsonian-specific:\n\n- Wraps the [Smithsonian Open Access API](https://edan.si.edu/openaccess/apidocs/) (14.5M objects across 20+ museums, 5.2M carrying CC0 media) with a free `api.data.gov` key\n- CC0 gating on `smithsonian_get_media` — only open-access images returned, never restricted content\n- Graceful degradation in `smithsonian_find_related` — a failure in one metadata signal doesn't abort the rest\n- Response normalization across heterogeneous museum metadata schemas\n\nAgent-friendly output:\n\n- `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)\n- Typed error reasons (`no_results`, `invalid_filter`, `not_found`, `no_media`, `no_images`, `not_cc0`, `invalid_id`) with recovery hints for each case\n- `similarity_signals` on related-object results let agents explain why objects were surfaced\n- `total_count` on all search responses enables agents to communicate result scope before paginating\n\n---\n\n## Getting started\n\n### Public Hosted Instance\n\nA public instance is available at `https://smithsonian.caseyjhand.com/mcp` — no installation required. Point any MCP client at it via Streamable HTTP:\n\n```json\n{\n \"mcpServers\": {\n \"smithsonian-mcp-server\": {\n \"type\": \"streamable-http\",\n \"url\": \"https://smithsonian.caseyjhand.com/mcp\"\n }\n }\n}\n```\n\n### Self-Hosted / Local\n\n> **Requires a free `api.data.gov` API key** — register at [https://api.data.gov/signup](https://api.data.gov/signup) and set `SMITHSONIAN_API_KEY` in your config.\n\nAdd the following to your MCP client configuration file:\n\n```json\n{\n \"mcpServers\": {\n \"smithsonian-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"bunx\",\n \"args\": [\"@cyanheads/smithsonian-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"SMITHSONIAN_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\nOr with npx (no Bun required):\n\n```json\n{\n \"mcpServers\": {\n \"smithsonian-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"npx\",\n \"args\": [\"-y\", \"@cyanheads/smithsonian-mcp-server@latest\"],\n \"env\": {\n \"MCP_TRANSPORT_TYPE\": \"stdio\",\n \"MCP_LOG_LEVEL\": \"info\",\n \"SMITHSONIAN_API_KEY\": \"your-api-key\"\n }\n }\n }\n}\n```\n\nOr with Docker:\n\n```json\n{\n \"mcpServers\": {\n \"smithsonian-mcp-server\": {\n \"type\": \"stdio\",\n \"command\": \"docker\",\n \"args\": [\n \"run\", \"-i\", \"--rm\",\n \"-e\", \"MCP_TRANSPORT_TYPE=stdio\",\n \"-e\", \"SMITHSONIAN_API_KEY=your-api-key\",\n \"ghcr.io/cyanheads/smithsonian-mcp-server:latest\"\n ]\n }\n }\n}\n```\n\nFor Streamable HTTP, set the transport and start the server:\n\n```sh\nMCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 SMITHSONIAN_API_KEY=your-api-key bun run start:http\n# Server listens at http://localhost:3010/mcp\n```\n\n### Prerequisites\n\n- [Bun v1.3.0](https://bun.sh/) or higher (or Node.js v24+).\n- A free `api.data.gov` API key — register at [https://api.data.gov/signup](https://api.data.gov/signup). Approval is instant.\n\n### Installation\n\n1. **Clone the repository:**\n\n```sh\ngit clone https://github.com/cyanheads/smithsonian-mcp-server.git\n```\n\n2. **Navigate into the directory:**\n\n```sh\ncd smithsonian-mcp-server\n```\n\n3. **Install dependencies:**\n\n```sh\nbun install\n```\n\n4. **Configure environment:**\n\n```sh\ncp .env.example .env\n# Edit .env and set SMITHSONIAN_API_KEY\n```\n\n---\n\n## Configuration\n\n| Variable | Description | Default |\n|:---------|:------------|:--------|\n| `SMITHSONIAN_API_KEY` | **Required.** Free API key from [api.data.gov/signup](https://api.data.gov/signup). | — |\n| `SMITHSONIAN_BASE_URL` | Smithsonian Open Access API base URL. | `https://api.si.edu/openaccess/api/v1.0` |\n| `SMITHSONIAN_TERMS_CACHE_TTL_SECONDS` | Seconds to cache each indexed field's term vocabulary. `0` disables caching. | `3600` |\n| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |\n| `MCP_HTTP_PORT` | Port for HTTP server. | `3010` |\n| `MCP_SESSION_MODE` | Session mode: `auto`, `stateful`, or `stateless`. This server explicitly uses stateless HTTP sessions. | `stateless` |\n| `MCP_AUTH_MODE` | Auth mode: `none`, `jwt`, or `oauth`. | `none` |\n| `MCP_LOG_LEVEL` | Log level (RFC 5424). | `info` |\n| `LOGS_DIR` | Directory for log files (Node.js only). | `/logs` |\n| `STORAGE_PROVIDER_TYPE` | Storage backend. | `in-memory` |\n| `OTEL_ENABLED` | Enable [OpenTelemetry instrumentation](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |\n\nSee [`.env.example`](./.env.example) for the full list of optional overrides.\n\n---\n\n## Running the server\n\n### Local development\n\n- **Build and run:**\n\n ```sh\n # One-time build\n bun run rebuild\n\n # Run the built server\n bun run start:stdio\n # or\n bun run start:http\n ```\n\n- **Run checks and tests:**\n\n ```sh\n bun run devcheck # Lint, format, typecheck, security\n bun run test # Vitest test suite\n bun run lint:mcp # Validate MCP definitions against spec\n ```\n\n### Docker\n\n```sh\ndocker build -t smithsonian-mcp-server .\ndocker run --rm -e SMITHSONIAN_API_KEY=your-api-key -p 3010:3010 smithsonian-mcp-server\n```\n\nThe 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.\n\n---\n\n## Project structure\n\n| Directory | Purpose |\n|:----------|:--------|\n| `src/index.ts` | `createApp()` entry point — registers tools and initializes the Smithsonian service. |\n| `src/config` | Server-specific environment variable parsing (`SMITHSONIAN_API_KEY`, `SMITHSONIAN_BASE_URL`, `SMITHSONIAN_TERMS_CACHE_TTL_SECONDS`). |\n| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). |\n| `src/services/smithsonian` | Smithsonian Open Access API client, normalization, and type definitions. |\n| `tests/` | Unit and integration tests. |\n| `docs/` | Design document and directory tree. |\n\n---\n\n## Development guide\n\nSee [`CLAUDE.md`](./CLAUDE.md) / [`AGENTS.md`](./AGENTS.md) for development guidelines and architectural rules. The short version:\n\n- Handlers throw, framework catches — no `try/catch` in tool logic\n- Use `ctx.log` for request-scoped logging, `ctx.state` for tenant-scoped storage\n- Register new tools via the barrel in `src/mcp-server/tools/definitions/index.ts`\n- Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields\n\n---\n\n## Contributing\n\nIssues and pull requests are welcome. Run checks and tests before submitting:\n\n```sh\nbun run devcheck\nbun run test\n```\n\n---\n\n## License\n\nApache-2.0 — see [LICENSE](LICENSE) for details.\n",
"bytes": 18357,
"sha": "23d3273ff2936f49c8a055b3184e8df21ecbc19b4fbf59dcb2f2f3e3b409f420",
"repo_slug": "cyanheads/smithsonian-mcp-server",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/mcp_io_github_cyanheads_smithsonian_mcp_serv_29243827/readme"
}