Smithsonian MCP Server
Enables searching and exploring millions of items from the Smithsonian Institution's collections including artifacts, artworks, specimens, photographs, and more, using the Smithsonian Open Access API.
README
Smithsonian MCP Server
A Model Context Protocol (MCP) server that provides access to the Smithsonian Institution's Open Access API. Search and explore millions of items from the Smithsonian's collections including artifacts, artworks, specimens, photographs, and more.
Features
- Search Collections: Search across millions of items from 19 Smithsonian museums and research centers
- Get Item Details: Retrieve comprehensive metadata about specific items
- Browse Categories: Discover available terms and filters for refining searches
- Online Media: Filter for items with images and other online media
Installation
Prerequisites
- Python 3.10 or higher
- A Smithsonian API key (free) - Get one at https://api.data.gov/signup/
Setup
- Clone the repository:
git clone https://github.com/AlexLin1234/smithsonian-mcp-server.git
cd smithsonian-mcp-server
- Install the package:
pip install -e .
- Set up your API key:
cp .env.example .env
# Edit .env and add your API key
Or set the environment variable directly:
export SMITHSONIAN_API_KEY=your_api_key_here
Configuration for Claude Desktop
Add this to your Claude Desktop configuration file:
MacOS
Location: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows
Location: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"smithsonian": {
"command": "python",
"args": [
"-m",
"smithsonian_mcp_server.server"
],
"env": {
"SMITHSONIAN_API_KEY": "api-key-here"
}
}
}
}
Alternatively, if you installed it in a virtual environment:
{
"mcpServers": {
"smithsonian": {
"command": "/path/to/venv/bin/python",
"args": [
"-m",
"smithsonian_mcp_server.server"
],
"env": {
"SMITHSONIAN_API_KEY": "your_api_key_here"
}
}
}
}
Available Tools
search_collection
Search the Smithsonian collections with flexible query options.
Parameters:
query(required): Search query string (supports keywords, phrases in quotes, AND/OR operators)rows(optional): Number of results to return (default: 10, max: 1000)start(optional): Starting offset for pagination (default: 0)online_media_only(optional): Only return items with online media/images (default: false)
Example:
Search for "space shuttle" items with images
get_item
Get detailed information about a specific item.
Parameters:
item_id(required): The Smithsonian item ID (obtained from search results)
Example:
Get details for item "edanmdm-NASM_A19600093000"
get_category_terms
Get available terms for a specific category or facet.
Parameters:
category(required): Category name (e.g., 'online_media_type', 'data_source', 'topic', 'place')starts_with(optional): Filter terms that start with this string
Example:
Get available topics starting with "Art"
Example Usage
Once configured in Claude Desktop, you can ask Claude questions like:
- "Search the Smithsonian for information about the Wright Brothers"
- "Find items related to ancient Egypt with images"
- "Show me artifacts from the Air and Space Museum"
- "Get details about item edanmdm-NASM_A19600093000"
- "What data sources are available in the Smithsonian API?"
API Information
This server uses the Smithsonian Open Access API v1.0:
- Base URL:
https://api.si.edu/openaccess/api/v1.0 - Documentation: https://www.si.edu/openaccess/devtools
- Collections: 2.8+ million open access items
- Coverage: 19 Smithsonian museums, research centers, and libraries
Development
Install Development Dependencies
pip install -e ".[dev]"
Run Tests
pytest
Code Formatting
black src/
ruff check src/
License
MIT License - See LICENSE file for details
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
For issues related to:
- This MCP server: Open an issue on GitHub
- The Smithsonian API: Visit https://www.si.edu/openaccess/faq
- Claude Desktop: Visit https://docs.claude.com
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。