Search, explore, and retrieve CC0 media from 19.4 million Smithsonian Open Access objects across 20+ museums via MCP. STDIO or Streamable HTTP.
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
git clone https://github.com/cyanheads/smithsonian-mcp-server{
"mcpServers": {
"smithsonian": {
"command": "node",
"args": ["/path/to/smithsonian-mcp-server/dist/index.js"],
"env": {
"SMITHSONIAN_API_KEY": "<smithsonian_api_key>"
}
}
}
}SMITHSONIAN_API_KEYMCP Servers overview
<div align="center">
<h1>@cyanheads/smithsonian-mcp-server</h1>
<p><b>Search, explore, and retrieve CC0 media from 19.4 million Smithsonian Open Access objects across 20+ museums via MCP. STDIO or Streamable HTTP.</b>
<div>6 Tools</div>
</p>
</div>
<div align="center">
[](./CHANGELOG.md) [](./LICENSE) [](https://github.com/users/cyanheads/packages/container/package/smithsonian-mcp-server) [](https://modelcontextprotocol.io/) [](https://www.npmjs.com/package/@cyanheads/smithsonian-mcp-server) [](https://www.typescriptlang.org/) [](https://bun.sh/)
</div>
<div align="center">
[](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)
[](https://www.npmjs.com/package/@cyanheads/mcp-ts-core)
</div>
<div align="center">
**Public Hosted Server:** [https://smithsonian.caseyjhand.com/mcp](https://smithsonian.caseyjhand.com/mcp)
</div>
---
## Prerequisites
> **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.
>
> **CC0 media gating:** `smithsonian_get_media` only returns CC0-licensed (open access) images. Use `smithsonian_search` with `filters.cc0_only: true` to find objects with downloadable media before calling it.
---
## Tools
Six tools covering the full Smithsonian Open Access workflow — filter vocabulary discovery, search, detail retrieval, CC0 image access, and cross-collection exploration:
| Tool | Description |
|:---|:---|
| `smithsonian_search` | Search across 19.4M objects by text query with optional filters (museum, type, decade, culture, place, online-only, CC0). Returns curated summaries with total count. |
| `smithsonian_list_terms` | Enumerate the valid term vocabulary for an indexed filter field (unit_code, object_type, culture, place, date). Call before filtering to avoid empty results from invalid values. |
| `smithsonian_get_object` | Fetch the full catalog record for an object by ID: title, dates, materials, dimensions, provenance, exhibition history, credit line, and identifiers. |
| `smithsonian_get_media` | Return all CC0-licensed images for an object at multiple resolutions (thumbnail, screen, high-res JPEG/TIFF). Only CC0 images returned — throws when none exist. |
| `smithsonian_explore` | Browse collections by category (museum, culture, period, medium) with total count, sample objects, and museum breakdown. Entry point for open-ended research. |
| `smithsonian_find_related` | Discover cross-collection objects related to an anchor via parallel fan-out searches across culture, maker, topic, and period signals. |
### `smithsonian_search`
Full-text search with structured filters across the entire Smithsonian catalog.
- Free-text search over 19.4M objects from 20+ museums
- Filters: museum unit code, object type, decade (`1920s`), culture, geographic place, online-only, CC0-only
- Returns curated summaries: title, 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`, `object_type`, `culture`, `place`, `date`, `media_usage`, `online_media_type`
- Returns terms sorted by object count descending — most-populated terms first
- Call this once per field to ground filter values; passing an invalid term to `smithsonian_search` produces empty results with no error
- Paginate with `start` + `rows` (default 50 per page, max 100)
---
### `smithsonian_get_object`
Full provenance metadata for a single object.
- Input: `record_id` from `smithsonian_search` — do not construct IDs manually
- Returns all available 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
- Each image entry includes thumbnail (~120px), screen-size (~800px), and high-resolution JPEG/TIFF URLs with pixel dimensions
- Use `smithsonian_search` with `filters.cc0_only: true` before calling this tool
---
### `smithsonian_explore`
Category-constrained browse for open-ended collection discovery.
- Four modes: `museum` (by unit code or full name), `culture` (e.g. `"Aztec"`), `period` (decade, e.g. `"1940s"`), `medium` (object type, e.g. `"Painting"`)
- Returns total count, representative sample objects, and a museum breakdown showing which institutions hold matching items
- Ideal entry point when the user wants to understand what the Smithsonian has about a topic
---
### `smithsonian_find_related`
Cross-collection discovery via parallel metadata fan-out.
- Fetches anchor object metadata, then fans out up to 4 parallel searches using culture, maker, topic, and period+type signals
- Deduplicates against the anchor and merges results ranked by number of matching signals
- 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 which metadata terms connected it to the anchor
---
## Features
Built on [`@cyanheads/mcp-ts-core`](https://www.npmjs.com/package/@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](https://edan.si.edu/openaccess/apidocs/) (19.4M objects across 20+ museums) with a free `api.data.gov` key
- CC0 gating on `smithsonian_get_media` — only open-access images returned, never restricted content
- Parallel fan-out in `smithsonian_find_related` with graceful degradation (partial failures don't abort)
- Response normalization across heterogeneous museum metadata schemas
Agent-friendly output:
- CC0 flags on every object summary — agents can gate image download calls without an extra lookup
- Typed error reasons (`no_results`, `not_found`, `not_cc0`, `no_media`, `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:
```json
{
"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](https://api.data.gov/signup) and set `SMITHSONIAN_API_KEY` in your config.
Add the following to your MCP client configuration file:
```json
{
"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):
```json
{
"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 DWhat people ask about smithsonian-mcp-server
What is cyanheads/smithsonian-mcp-server?
+
cyanheads/smithsonian-mcp-server is mcp servers for the Claude AI ecosystem. Search, explore, and retrieve CC0 media from 19.4 million Smithsonian Open Access objects across 20+ museums via MCP. STDIO or Streamable HTTP. It has 1 GitHub stars and was last updated 2d ago.
How do I install smithsonian-mcp-server?
+
You can install smithsonian-mcp-server by cloning the repository (https://github.com/cyanheads/smithsonian-mcp-server) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is cyanheads/smithsonian-mcp-server safe to use?
+
Our security agent has analyzed cyanheads/smithsonian-mcp-server and assigned a Trust Score of 87/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.
Who maintains cyanheads/smithsonian-mcp-server?
+
cyanheads/smithsonian-mcp-server is maintained by cyanheads. The last recorded GitHub activity is from 2d ago, with 0 open issues.
Are there alternatives to smithsonian-mcp-server?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy smithsonian-mcp-server to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/cyanheads-smithsonian-mcp-server)<a href="https://claudewave.com/repo/cyanheads-smithsonian-mcp-server"><img src="https://claudewave.com/api/badge/cyanheads-smithsonian-mcp-server" alt="Featured on ClaudeWave: cyanheads/smithsonian-mcp-server" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。AI 智能筛选新闻 + AI 翻译 + AI 分析简报直推手机,也支持接入 MCP 架构,赋能 AI 自然语言对话分析、情感洞察与趋势预测等。支持 Docker ,数据本地/云端自持。集成微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 等渠道智能推送。